diff --git a/.github/workflows/build-msys.yml b/.github/workflows/build-msys.yml index c2633c151a58..15c55cf12ccc 100644 --- a/.github/workflows/build-msys.yml +++ b/.github/workflows/build-msys.yml @@ -27,8 +27,8 @@ jobs: fail-fast: false matrix: include: - - { sys: UCRT64, env: ucrt-x86_64, build: Release } - - { sys: CLANG64, env: clang-x86_64, build: Release } + - { sys: UCRT64, env: ucrt-x86_64, compiler: gcc, build: Release } + - { sys: CLANG64, env: clang-x86_64, compiler: clang, build: Release } steps: - name: Clone @@ -48,9 +48,7 @@ jobs: update: true msystem: ${{matrix.sys}} install: >- - base-devel - git - mingw-w64-${{matrix.env}}-toolchain + mingw-w64-${{matrix.env}}-${{matrix.compiler}} mingw-w64-${{matrix.env}}-cmake mingw-w64-${{matrix.env}}-openblas diff --git a/.pi/gg/SYSTEM.md b/.pi/gg/SYSTEM.md index 06d97ae78ee2..197173faed80 100644 --- a/.pi/gg/SYSTEM.md +++ b/.pi/gg/SYSTEM.md @@ -16,12 +16,12 @@ Pull requests (PRs): - New branch names are prefixed with "gg/" - Before opening a pull request, ask the user to confirm the description - When creating a pull request, look for the repository's PR template and follow it -- For the AI usage disclosure section, write "YES. llama.cpp + pi + [MODEL]" +- For the AI usage disclosure section, write "YES. pi:llama.cpp/[MODEL]" - Ask the user to tell you what model was used and write it in place of [MODEL] - Always create the pull requests in draft mode Commits: -- On every commit that you make, include a "Assisted-by: llama.cpp:local pi" tag +- On every commit that you make, include a "Assisted-by: pi:llama.cpp/[MODEL]" tag - Do not explicitly set the git author in commits - rely on the default git config - Always use `--no-gpg-sign` when committing - Never `git push` without explicit confirmation from the user diff --git a/common/CMakeLists.txt b/common/CMakeLists.txt index 1a56c25857fa..c42320c46b16 100644 --- a/common/CMakeLists.txt +++ b/common/CMakeLists.txt @@ -78,6 +78,8 @@ add_library(${TARGET} hf-cache.cpp hf-cache.h http.h + imatrix-loader.cpp + imatrix-loader.h json-partial.cpp json-partial.h json-schema-to-grammar.cpp diff --git a/common/arg.cpp b/common/arg.cpp index f53b4798105e..1ffaf704858d 100644 --- a/common/arg.cpp +++ b/common/arg.cpp @@ -446,6 +446,12 @@ bool common_params_handle_models(common_params & params, llama_example curr_ex) opts.download_mtp = spec_type_draft_mtp; opts.download_mmproj = !params.no_mmproj; + // sub-models (draft, mmproj, vocoder) are explicitly specified by the user, + // so we should not auto-discover mtp/mmproj siblings for them + common_download_opts sub_opts = opts; + sub_opts.download_mtp = false; + sub_opts.download_mmproj = false; + try { auto res = common_params_handle_model(params.model, opts); if (params.no_mmproj) { @@ -457,7 +463,7 @@ bool common_params_handle_models(common_params & params, llama_example curr_ex) // only download mmproj if the current example is using it for (const auto & ex : mmproj_examples) { if (curr_ex == ex) { - common_params_handle_model(params.mmproj, opts); + common_params_handle_model(params.mmproj, sub_opts); break; } } @@ -470,8 +476,8 @@ bool common_params_handle_models(common_params & params, llama_example curr_ex) params.speculative.draft.mparams.url.empty()) { params.speculative.draft.mparams.path = res.mtp.path; } - common_params_handle_model(params.speculative.draft.mparams, opts); - common_params_handle_model(params.vocoder.model, opts); + common_params_handle_model(params.speculative.draft.mparams, sub_opts); + common_params_handle_model(params.vocoder.model, sub_opts); return true; } catch (const common_skip_download_exception &) { return false; diff --git a/common/imatrix-loader.cpp b/common/imatrix-loader.cpp new file mode 100644 index 000000000000..efe9aecee3f8 --- /dev/null +++ b/common/imatrix-loader.cpp @@ -0,0 +1,165 @@ +#include "imatrix-loader.h" +#include "common.h" +#include "log.h" +#include "gguf.h" + +#include +#include +#include + +static bool common_imatrix_load_legacy(const std::string & fname, common_imatrix & imatrix) { + std::ifstream in(fname, std::ios::binary); + if (!in) { + LOG_ERR("%s: failed to open %s\n", __func__, fname.c_str()); + return false; + } + + int n_entries; + in.read((char *) &n_entries, sizeof(n_entries)); + if (in.fail() || n_entries < 1) { + LOG_ERR("%s: no data in file %s\n", __func__, fname.c_str()); + return false; + } + + for (int i = 0; i < n_entries; ++i) { + int32_t len = 0; + in.read((char *) &len, sizeof(len)); + std::vector name_as_vec(len + 1); + in.read((char *) name_as_vec.data(), len); + if (in.fail()) { + LOG_ERR("%s: failed reading name for entry %d from %s\n", __func__, i + 1, fname.c_str()); + return false; + } + name_as_vec[len] = 0; + std::string name{ name_as_vec.data() }; + + int32_t ncall = 0; + in.read((char *) &ncall, sizeof(ncall)); + int32_t nval = 0; + in.read((char *) &nval, sizeof(nval)); + if (in.fail() || nval < 1) { + LOG_ERR("%s: failed reading number of values for entry %d\n", __func__, i); + return false; + } + + auto & e = imatrix.entries[std::move(name)]; + e.sums.resize(nval); + in.read((char *) e.sums.data(), nval * sizeof(float)); + if (in.fail()) { + LOG_ERR("%s: failed reading data for entry %d\n", __func__, i); + return false; + } + + e.counts.resize(1); + e.counts[0] = ncall; + } + + // the trailing data (chunk count + dataset name) is optional + if (in.peek() != EOF) { + int32_t n_calls = 0; + in.read((char *) &n_calls, sizeof(n_calls)); + imatrix.chunk_count = n_calls; + + if (!in.fail()) { + int32_t len = 0; + in.read((char *) &len, sizeof(len)); + if (!in.fail() && len > 0) { + std::vector dataset(len + 1, 0); + in.read(dataset.data(), len); + if (!in.fail()) { + imatrix.datasets.push_back(dataset.data()); + } + } + } + } + + imatrix.chunk_size = 0; + imatrix.is_legacy = true; + + return true; +} + +bool common_imatrix_load(const std::string & fname, common_imatrix & imatrix) { + struct ggml_context * ctx = nullptr; + struct gguf_init_params meta_gguf_params = { + /* .no_alloc = */ false, + /* .ctx = */ &ctx, + }; + struct gguf_context * ctx_gguf = gguf_init_from_file(fname.c_str(), meta_gguf_params); + if (!ctx_gguf) { + return common_imatrix_load_legacy(fname, imatrix); + } + + const int32_t n_entries = gguf_get_n_tensors(ctx_gguf); + if (n_entries < 1) { + LOG_ERR("%s: no data in file %s\n", __func__, fname.c_str()); + gguf_free(ctx_gguf); + ggml_free(ctx); + return false; + } + + const int64_t datasets_key = gguf_find_key(ctx_gguf, LLM_KV_IMATRIX_DATASETS); + const int64_t chunk_count_key = gguf_find_key(ctx_gguf, LLM_KV_IMATRIX_CHUNK_COUNT); + const int64_t chunk_size_key = gguf_find_key(ctx_gguf, LLM_KV_IMATRIX_CHUNK_SIZE); + + if (datasets_key != -1 && gguf_get_arr_type(ctx_gguf, datasets_key) == GGUF_TYPE_STRING) { + const int64_t n = gguf_get_arr_n(ctx_gguf, datasets_key); + imatrix.datasets.reserve(imatrix.datasets.size() + n); + for (int64_t i = 0; i < n; ++i) { + imatrix.datasets.push_back(gguf_get_arr_str(ctx_gguf, datasets_key, i)); + } + } + + imatrix.has_metadata = (datasets_key != -1 && chunk_count_key != -1 && chunk_size_key != -1); + imatrix.chunk_count = (chunk_count_key != -1) ? gguf_get_val_u32(ctx_gguf, chunk_count_key) : 0; + imatrix.chunk_size = (chunk_size_key != -1) ? gguf_get_val_u32(ctx_gguf, chunk_size_key) : 0; + + const std::string in_sum2_suffix{ ".in_sum2" }; + const std::string counts_suffix{ ".counts" }; + + std::map> sums_counts_for; + + for (struct ggml_tensor * cur = ggml_get_first_tensor(ctx); cur; cur = ggml_get_next_tensor(ctx, cur)) { + std::string name = cur->name; + + if (name.empty()) { continue; } + + if (string_remove_suffix(name, in_sum2_suffix)) { + sums_counts_for[std::move(name)].first = cur; + } else if (string_remove_suffix(name, counts_suffix)) { + sums_counts_for[std::move(name)].second = cur; + } + } + + for (const auto & sc : sums_counts_for) { + const std::string & name = sc.first; + const struct ggml_tensor * in_sum2 = sc.second.first; + const struct ggml_tensor * counts = sc.second.second; + + if (!in_sum2 || !counts) { + LOG_ERR("%s: mismatched sums and counts for %s\n", __func__, name.c_str()); + gguf_free(ctx_gguf); + ggml_free(ctx); + return false; + } + + auto & e = imatrix.entries[name]; + + const int64_t nval = ggml_nelements(in_sum2); + const int64_t ncounts = ggml_nelements(counts); + + e.sums.resize(nval); + for (int64_t j = 0; j < nval; ++j) { + e.sums[j] = ((const float *) in_sum2->data)[j]; + } + + e.counts.resize(ncounts); + for (int64_t j = 0; j < ncounts; ++j) { + e.counts[j] = std::lround(((const float *) counts->data)[j]); + } + } + + gguf_free(ctx_gguf); + ggml_free(ctx); + return true; +} diff --git a/common/imatrix-loader.h b/common/imatrix-loader.h new file mode 100644 index 000000000000..ed00d724ac85 --- /dev/null +++ b/common/imatrix-loader.h @@ -0,0 +1,26 @@ +#pragma once + +#include +#include +#include +#include + +inline constexpr const char * LLM_KV_IMATRIX_DATASETS = "imatrix.datasets"; +inline constexpr const char * LLM_KV_IMATRIX_CHUNK_COUNT = "imatrix.chunk_count"; +inline constexpr const char * LLM_KV_IMATRIX_CHUNK_SIZE = "imatrix.chunk_size"; + +struct common_imatrix_entry { + std::vector sums; + std::vector counts; +}; + +struct common_imatrix { + std::map entries; + std::vector datasets; + int32_t chunk_count = 0; + int32_t chunk_size = 0; + bool is_legacy = false; + bool has_metadata = false; +}; + +bool common_imatrix_load(const std::string & fname, common_imatrix & imatrix); diff --git a/common/speculative.cpp b/common/speculative.cpp index aa0d0ed86b24..e4fe2a86eb71 100644 --- a/common/speculative.cpp +++ b/common/speculative.cpp @@ -418,6 +418,8 @@ struct common_speculative_impl_draft_mtp : public common_speculative_impl { int32_t n_embd = 0; + bool kv_shared_with_target = false; + // Per-sequence cross-batch carryover: pair (h_p, x_{p+1}) at MTP pos p+1. // The last h-row of one process() call needs the first token of the NEXT // call to pair with, so it's stashed here until that next call fires. @@ -444,7 +446,9 @@ struct common_speculative_impl_draft_mtp : public common_speculative_impl { auto * ctx_dft = this->params.ctx_dft; GGML_ASSERT(ctx_tgt && ctx_dft && "MTP requires ctx_tgt and ctx_dft to be set"); - n_embd = llama_model_n_embd(llama_get_model(ctx_dft)); + n_embd = llama_model_n_embd_out(llama_get_model(ctx_dft)); + GGML_ASSERT(n_embd == llama_model_n_embd(llama_get_model(ctx_tgt)) && + "MTP input row width must match the target h_nextn width"); LOG_INF("%s: adding speculative implementation 'draft-mtp'\n", __func__); LOG_INF("%s: - n_max=%d, n_min=%d, p_min=%.2f, n_embd=%d, backend_sampling=%d\n", __func__, this->params.n_max, this->params.n_min, this->params.p_min, n_embd, (int) this->params.backend_sampling); @@ -487,8 +491,11 @@ struct common_speculative_impl_draft_mtp : public common_speculative_impl { } } + kv_shared_with_target = llama_get_memory(ctx_dft) == nullptr; + llama_set_embeddings_nextn(ctx_tgt, true, /*masked*/ false); llama_set_embeddings_nextn(ctx_dft, true, /*masked*/ true); + llama_set_mtp_source(ctx_dft, ctx_tgt); pending_h.assign(n_seq, std::vector(n_embd, 0.0f)); @@ -526,9 +533,10 @@ struct common_speculative_impl_draft_mtp : public common_speculative_impl { if (N <= 0) { return; } + auto * ctx_dft = this->params.ctx_dft; const llama_pos pos_max = llama_memory_seq_pos_max(llama_get_memory(ctx_dft), seq_id); - if (pos_max < N - 1) { + if (pos_max < N - 1 && !kv_shared_with_target) { LOG_WRN("%s: ctx_dft pos_max=%d < N-1=%d - " "process() hook may not have run on every prefill ubatch " "(need_embd / logits=1 on every prompt position?). " @@ -571,48 +579,42 @@ struct common_speculative_impl_draft_mtp : public common_speculative_impl { const size_t row_bytes = (size_t) n_embd * sizeof(float); - common_batch_clear(batch); + // if kv is shared with target (e.g Gemma4), then we can skip this catch-up decode + if (!kv_shared_with_target) { + common_batch_clear(batch); - for (int k = 0; k < n_tokens; ++k) { - common_batch_add(batch, batch_in.token[k], batch_in.pos[k], { batch_in.seq_id[k][0] }, 0); - } + for (int k = 0; k < n_tokens; ++k) { + common_batch_add(batch, batch_in.token[k], batch_in.pos[k], { batch_in.seq_id[k][0] }, 0); + } - // shift the tgt embeddings to the right by one position - // assumes that the tokens in the batch are sequential for each sequence - // i.e. we cannot have seq_id like this: [0, 0, 0, 1, 1, 0, 1, 1] - // ^--- this is a problem - // TODO:this is generally true, but would be nice to assert it - { - const float * h_tgt = llama_get_embeddings_nextn(ctx_tgt); - std::memcpy(batch.embd + (size_t) 1 * n_embd, h_tgt, row_bytes * (n_tokens-1)); + // shift the tgt embeddings to the right by one position + // assumes that the tokens in the batch are sequential for each sequence + // i.e. we cannot have seq_id like this: [0, 0, 0, 1, 1, 0, 1, 1] + // ^--- this is a problem + // TODO:this is generally true, but would be nice to assert it + { + const float * h_tgt = llama_get_embeddings_nextn(ctx_tgt); + std::memcpy(batch.embd + (size_t) 1 * n_embd, h_tgt, row_bytes * (n_tokens-1)); + } - //{ - // // string with seq_ids in the batch - // std::stringstream ss; - // for (int i = 0; i < n_tokens; ++i) { - // ss << batch_in.seq_id[i][0] << ","; - // } - // LOG_WRN("%s: batch_in.seq_id = %s\n", __func__, ss.str().c_str()); - //} - } + // fill the pending embeddings from a previous run + auto set_h = [&](int idx, const float * h_row) { + std::memcpy(batch.embd + (size_t) idx * n_embd, h_row, row_bytes); + }; - // fill the pending embeddings from a previous run - auto set_h = [&](int idx, const float * h_row) { - std::memcpy(batch.embd + (size_t) idx * n_embd, h_row, row_bytes); - }; + for (llama_seq_id seq_id = 0; seq_id < (llama_seq_id) n_seq; ++seq_id) { + if (i_batch_beg[seq_id] < 0) { + continue; + } - for (llama_seq_id seq_id = 0; seq_id < (llama_seq_id) n_seq; ++seq_id) { - if (i_batch_beg[seq_id] < 0) { - continue; + set_h(i_batch_beg[seq_id], pending_h[seq_id].data()); } - set_h(i_batch_beg[seq_id], pending_h[seq_id].data()); - } - - const int32_t rc = llama_decode(ctx_dft, batch); - if (rc != 0) { - LOG_ERR("%s: llama_decode(ctx_dft) failed rc=%d (pos=%d)\n", __func__, (int) rc, (int) batch_in.pos[0]); - return false; + const int32_t rc = llama_decode(ctx_dft, batch); + if (rc != 0) { + LOG_ERR("%s: llama_decode(ctx_dft) failed rc=%d (pos=%d)\n", __func__, (int) rc, (int) batch_in.pos[0]); + return false; + } } for (llama_seq_id seq_id = 0; seq_id < (llama_seq_id) n_seq; ++seq_id) { diff --git a/conversion/__init__.py b/conversion/__init__.py index 2c79580f8a36..308bdaff4497 100644 --- a/conversion/__init__.py +++ b/conversion/__init__.py @@ -75,9 +75,11 @@ "Gemma3TextModel": "gemma", "Gemma3nForCausalLM": "gemma", "Gemma3nForConditionalGeneration": "gemma", + "Gemma4AssistantForCausalLM": "gemma", "Gemma4ForConditionalGeneration": "gemma", "Gemma4ForCausalLM": "gemma", "Gemma4UnifiedForConditionalGeneration": "gemma", + "Gemma4UnifiedAssistantForCausalLM": "gemma", "GemmaForCausalLM": "gemma", "Glm4ForCausalLM": "glm", "Glm4MoeForCausalLM": "glm", diff --git a/conversion/gemma.py b/conversion/gemma.py index 379876629fbf..d06c9e195385 100644 --- a/conversion/gemma.py +++ b/conversion/gemma.py @@ -785,6 +785,16 @@ def set_gguf_parameters(self): self.gguf_writer.add_suppress_tokens(suppress_tokens) +@ModelBase.register("Gemma4AssistantForCausalLM", "Gemma4UnifiedAssistantForCausalLM") +class Gemma4AssistantModel(Gemma4Model): + model_arch = gguf.MODEL_ARCH.GEMMA4_ASSISTANT + + def set_gguf_parameters(self): + super().set_gguf_parameters() + self.gguf_writer.add_embedding_length_out(self.hparams["backbone_hidden_size"]) + self.gguf_writer.add_nextn_predict_layers(self.block_count) + + @ModelBase.register("Gemma4ForConditionalGeneration") class Gemma4VisionAudioModel(MmprojModel): has_audio_encoder = True diff --git a/examples/speculative-simple/speculative-simple.cpp b/examples/speculative-simple/speculative-simple.cpp index 5325bcc9e3fb..d87ba48beb14 100644 --- a/examples/speculative-simple/speculative-simple.cpp +++ b/examples/speculative-simple/speculative-simple.cpp @@ -175,7 +175,7 @@ int main(int argc, char ** argv) { llama_memory_seq_pos_max(llama_get_memory(ctx_tgt), seq_id)); if (use_ckpt_dft) { - ckpt.update_dft(ctx_dft.get(), seq_id, LLAMA_STATE_SEQ_FLAGS_PARTIAL_ONLY | LLAMA_STATE_SEQ_FLAGS_ON_DEVICE); + ckpt.update_dft(ctx_dft.get(), seq_id, LLAMA_STATE_SEQ_FLAGS_PARTIAL_ONLY); } // generate a new draft @@ -196,12 +196,12 @@ int main(int argc, char ** argv) { // this allows us to restore the state if partial draft acceptance occurs if (!draft.empty()) { if (use_ckpt_tgt) { - ckpt.update_tgt(ctx_tgt, seq_id, LLAMA_STATE_SEQ_FLAGS_PARTIAL_ONLY | LLAMA_STATE_SEQ_FLAGS_ON_DEVICE); + ckpt.update_tgt(ctx_tgt, seq_id, LLAMA_STATE_SEQ_FLAGS_PARTIAL_ONLY); } } { - ckpt.load_dft(ctx_dft.get(), seq_id, LLAMA_STATE_SEQ_FLAGS_PARTIAL_ONLY | LLAMA_STATE_SEQ_FLAGS_ON_DEVICE); + ckpt.load_dft(ctx_dft.get(), seq_id, LLAMA_STATE_SEQ_FLAGS_PARTIAL_ONLY); llama_memory_seq_rm(llama_get_memory(ctx_dft.get()), seq_id, ckpt.pos_max + 1, -1); } @@ -261,13 +261,13 @@ int main(int argc, char ** argv) { draft = std::move(ids); { - ckpt.load_tgt(ctx_tgt, seq_id, LLAMA_STATE_SEQ_FLAGS_PARTIAL_ONLY | LLAMA_STATE_SEQ_FLAGS_ON_DEVICE); + ckpt.load_tgt(ctx_tgt, seq_id, LLAMA_STATE_SEQ_FLAGS_PARTIAL_ONLY); llama_memory_seq_rm(llama_get_memory(ctx_tgt), seq_id, ckpt.pos_max + 1, -1); } { - ckpt.load_dft(ctx_dft.get(), seq_id, LLAMA_STATE_SEQ_FLAGS_PARTIAL_ONLY | LLAMA_STATE_SEQ_FLAGS_ON_DEVICE); + ckpt.load_dft(ctx_dft.get(), seq_id, LLAMA_STATE_SEQ_FLAGS_PARTIAL_ONLY); llama_memory_seq_rm(llama_get_memory(ctx_dft.get()), seq_id, ckpt.pos_max + 1, -1); } diff --git a/ggml/src/ggml-cpu/kleidiai/kleidiai.cpp b/ggml/src/ggml-cpu/kleidiai/kleidiai.cpp index 0ecf7ae02ac7..9e54b676b93f 100644 --- a/ggml/src/ggml-cpu/kleidiai/kleidiai.cpp +++ b/ggml/src/ggml-cpu/kleidiai/kleidiai.cpp @@ -38,6 +38,7 @@ #include "kleidiai.h" #include "ggml-cpu.h" +#include "ggml-cpu-impl.h" #include "ggml-impl.h" #include "ggml-backend-impl.h" #include "ggml-threading.h" @@ -61,7 +62,8 @@ struct ggml_kleidiai_context { ggml_kleidiai_kernels * kernels_q8; int sme_thread_cap; // <= 0 means “SME disabled/unknown”; int thread_hint; // <= 0 means “no hint” -} static ctx = { CPU_FEATURE_NONE, nullptr, nullptr, 0, -1 }; + int chunk_multiplier; +} static ctx = { CPU_FEATURE_NONE, nullptr, nullptr, 0, -1, 4 }; static const char* cpu_feature_to_string(cpu_feature f) { if (f == CPU_FEATURE_NONE) { @@ -186,8 +188,9 @@ static void init_kleidiai_context(void) { if (!initialized) { initialized = true; - const char *env_sme = getenv("GGML_KLEIDIAI_SME"); - const char *env_threads = getenv("GGML_TOTAL_THREADS"); + const char *env_sme = getenv("GGML_KLEIDIAI_SME"); + const char *env_threads = getenv("GGML_TOTAL_THREADS"); + const char *env_chunk_mult = getenv("GGML_KLEIDIAI_CHUNK_MULTIPLIER"); const bool cpu_has_sme = ggml_cpu_has_sme(); size_t detected_smcus = 0; @@ -204,6 +207,14 @@ static void init_kleidiai_context(void) { } } + if (env_chunk_mult) { + bool ok = false; + int multiplier = parse_uint_env(env_chunk_mult, "GGML_KLEIDIAI_CHUNK_MULTIPLIER", &ok); + if (ok && multiplier > 0) { + ctx.chunk_multiplier = multiplier; + } + } + // SME policy: // - If CPU doesn't support SME: SME always off. // - Else: @@ -296,6 +307,50 @@ static inline size_t align_up(size_t value, size_t alignment) { return remainder == 0 ? value : value + (alignment - remainder); } +static inline size_t gcd_size(size_t a, size_t b) { + while (b != 0) { + const size_t t = a % b; + a = b; + b = t; + } + return a; +} + +static inline bool lcm_size(size_t a, size_t b, size_t & result) { + if (a == 0 || b == 0) { + result = 0; + return false; + } + const size_t g = gcd_size(a, b); + const size_t q = a / g; + if (q > SIZE_MAX / b) { + return false; + } + result = q * b; + return true; +} + +static inline size_t ceil_div_size(size_t a, size_t b) { + return b == 0 ? 0 : (a + b - 1) / b; +} + +struct kleidiai_block_args { + size_t lhs_bl; + size_t rhs_bl; + size_t pack_bl; +}; + +static inline kleidiai_block_args kleidiai_get_block_args(ggml_type rhs_type) { + switch (rhs_type) { + case GGML_TYPE_Q4_0: + return { QK4_0, QK4_0, QK4_0 }; + case GGML_TYPE_Q8_0: + return { 0, 0, QK8_0 }; + default: + return { 0, 0, 0 }; + } +} + static inline bool kleidiai_pack_fallback_allowed() { if (ctx.sme_thread_cap <= 0) { return false; @@ -746,8 +801,10 @@ class tensor_traits : public ggml::cpu::tensor_traits { size_t n_step; size_t lhs_packed_size; size_t lhs_offset; - size_t n_offset; - size_t n_cols; + size_t lhs_bl; + size_t rhs_bl; + size_t pack_bl; + size_t lhs_packed_offset0; int assigned_threads; int thread_begin; int thread_end; @@ -772,6 +829,8 @@ class tensor_traits : public ggml::cpu::tensor_traits { continue; } + const kleidiai_block_args block_args = kleidiai_get_block_args(kernels->rhs_type); + runtime[runtime_count] = { slot, kernels, @@ -784,7 +843,9 @@ class tensor_traits : public ggml::cpu::tensor_traits { kinfo->get_n_step(), 0, 0, - 0, + block_args.lhs_bl, + block_args.rhs_bl, + block_args.pack_bl, 0, 0, 0, @@ -795,45 +856,8 @@ class tensor_traits : public ggml::cpu::tensor_traits { } if (runtime_count == 0) { - ggml_kleidiai_kernels * fallback = ggml_kleidiai_select_kernels(ctx.features, dst); - if (!fallback) { - return false; - } - kernel_info * kinfo = is_gemv ? &fallback->gemv : &fallback->gemm; - lhs_packing_info * linfo = is_gemv ? &fallback->gemv_lhs_info : &fallback->gemm_lhs_info; - rhs_packing_info * rinfo = &fallback->rhs_info; - if (!kinfo || !linfo || !linfo->packed_size_ex || !linfo->pack_func_ex || - !kinfo->get_rhs_packed_offset_ex || !kinfo->run_kernel_ex || !kinfo->get_dst_offset || - !rinfo || !rinfo->pack_func_ex || !rinfo->packed_size_ex) { - return false; - } - kernel_chain[0] = fallback; - runtime[0] = { - 0, - fallback, - kinfo, - linfo, - kinfo->get_mr(), - kinfo->get_nr(), - kinfo->get_kr(), - kinfo->get_sr(), - kinfo->get_n_step(), - 0, - 0, - 0, - 0, - 0, - 0, - 0, - nullptr - }; - size_t rhs_size_fallback = 0; - const uint8_t * rhs_base = weight_for_slot(0, rhs_size_fallback); - if (!rhs_base) { - rhs_base = static_cast(src0->data); - } - runtime[0].rhs_base = rhs_base; - runtime_count = 1; + GGML_LOG_WARN("kleidiai: no runtime kernel slot available for supported op %s\n", dst->name); + return false; } const int nth_total = params->nth > 0 ? params->nth : 1; @@ -846,6 +870,13 @@ class tensor_traits : public ggml::cpu::tensor_traits { break; } } + int non_sme_slot = -1; + for (int i = 0; i < runtime_count; ++i) { + if ((runtime[i].kernels->required_cpu & CPU_FEATURE_SME) != CPU_FEATURE_SME) { + non_sme_slot = i; + break; + } + } const int sme_cap_limit = ctx.sme_thread_cap; const bool use_hybrid = sme_cap_limit > 0 && @@ -864,12 +895,15 @@ class tensor_traits : public ggml::cpu::tensor_traits { if (!hybrid_enabled) { int chosen_slot = 0; if (too_small_for_hybrid && sme_slot != -1) { - chosen_slot = sme_slot; + chosen_slot = nth_total > sme_cap_limit && non_sme_slot != -1 ? non_sme_slot : sme_slot; } else if (runtime_count > 1 && ctx.sme_thread_cap > 0 && nth_total > ctx.sme_thread_cap) { chosen_slot = 1; } if (chosen_slot != 0 && chosen_slot < runtime_count) { runtime[0] = runtime[chosen_slot]; + runtime[0].assigned_threads = 0; + runtime[0].thread_begin = 0; + runtime[0].thread_end = 0; } runtime_count = runtime_count > 0 ? 1 : 0; @@ -896,6 +930,8 @@ class tensor_traits : public ggml::cpu::tensor_traits { int fallback_indices[GGML_KLEIDIAI_MAX_KERNEL_SLOTS]; int fallback_count = 0; + // The current hybrid chain is bounded to SME + one non-SME fallback slot. + GGML_ASSERT(GGML_KLEIDIAI_MAX_KERNEL_SLOTS == 2); for (int i = 0; i < runtime_count; ++i) { if (i == sme_slot) { continue; @@ -952,73 +988,67 @@ class tensor_traits : public ggml::cpu::tensor_traits { size_t cursor = 0; for (int i = 0; i < runtime_count; ++i) { - const ggml_type slot_rhs_type = runtime[i].kernels->rhs_type; - const size_t slot_pack_size_arg = slot_rhs_type == GGML_TYPE_Q4_0 ? QK4_0 : - slot_rhs_type == GGML_TYPE_Q8_0 ? QK8_0 : 0; - runtime[i].lhs_packed_size = runtime[i].lhs_info->packed_size_ex(m, k, slot_pack_size_arg, runtime[i].mr, runtime[i].kr, runtime[i].sr); + runtime[i].lhs_packed_size = runtime[i].lhs_info->packed_size_ex(m, k, runtime[i].pack_bl, runtime[i].mr, runtime[i].kr, runtime[i].sr); cursor = align_up(cursor, GGML_KLEIDIAI_PACK_ALIGN); runtime[i].lhs_offset = cursor; + runtime[i].lhs_packed_offset0 = runtime[i].lhs_info->get_packed_offset_ex(0, k, runtime[i].lhs_bl, runtime[i].mr, runtime[i].kr, runtime[i].sr); cursor += runtime[i].lhs_packed_size; } GGML_ASSERT(cursor <= params->wsize); uint8_t * scratch = static_cast(params->wdata); - size_t assigned_cols = 0; - uint64_t weighted_total = 0; - if (runtime_count > 1 && sme_slot != -1) { - for (int i = 0; i < runtime_count; ++i) { - const uint64_t weight = (i == sme_slot) ? (sme_cap << 1) : 1; - weighted_total += (uint64_t)runtime[i].assigned_threads * weight; - } - } + size_t common_step = 1; for (int i = 0; i < runtime_count; ++i) { - runtime[i].n_offset = assigned_cols; if (runtime[i].assigned_threads == 0) { - runtime[i].n_cols = 0; continue; } - const size_t remaining_cols = n - assigned_cols; - if (remaining_cols == 0) { - runtime[i].n_cols = 0; - continue; - } - const size_t step = runtime[i].n_step ? runtime[i].n_step : 1; - size_t target = 0; - if (weighted_total > 0) { - const uint64_t weight = (i == sme_slot) ? (sme_cap << 1) : 1; - target = (size_t)(((uint64_t)n * runtime[i].assigned_threads * weight) / weighted_total); - } else { - target = (size_t)(((uint64_t)n * runtime[i].assigned_threads) / nth_total); - } - target = std::min(target, remaining_cols); - size_t aligned = round_down(target, step); - if (aligned == 0 && remaining_cols >= step) { - aligned = step; + size_t next_step = 0; + if (!lcm_size(common_step, runtime[i].n_step ? runtime[i].n_step : 1, next_step)) { + return false; } - runtime[i].n_cols = aligned; - assigned_cols += aligned; + common_step = next_step; } - - if (assigned_cols < n) { - for (int i = runtime_count - 1; i >= 0; --i) { - if (runtime[i].assigned_threads > 0) { - runtime[i].n_cols += n - assigned_cols; - break; - } - } + GGML_ASSERT(common_step > 0); + + const bool disable_chunking = ggml_is_numa(); + const size_t chunk_multiplier = std::max(1, ctx.chunk_multiplier); + const size_t chunk_divisor = (nth_total == 1 || disable_chunking) ? (size_t)nth_total : (size_t)nth_total * chunk_multiplier; + size_t chunk_cols = align_up(std::max(1, ceil_div_size(n, chunk_divisor)), common_step); + if (chunk_cols == 0) { + chunk_cols = common_step; } + // If common_step is larger than n, the loop below runs one valid tail chunk + // with cols == n. + const size_t nchunk_size = std::max(1, ceil_div_size(n, chunk_cols)); + GGML_ASSERT(nchunk_size <= (size_t)INT_MAX); + const int nchunk = (int)nchunk_size; const size_t dst_stride = dst->nb[1]; + auto run_chunk = [&](runtime_slot & slot, size_t global_start, size_t cols, uint8_t * dst_batch_base) { + const size_t rhs_packed_offset = slot.kernel->get_rhs_packed_offset_ex(global_start, k, slot.rhs_bl); + const size_t dst_offset = slot.kernel->get_dst_offset(0, global_start, dst_stride); + + const uint8_t * lhs_ptr = scratch + slot.lhs_offset + slot.lhs_packed_offset0; + const uint8_t * rhs_ptr = slot.rhs_base + rhs_packed_offset; + float * dst_ptr = reinterpret_cast(dst_batch_base + dst_offset); + + slot.kernel->run_kernel_ex(m, cols, k, slot.rhs_bl, + lhs_ptr, + rhs_ptr, + dst_ptr, + dst_stride, + sizeof(float), + -FLT_MAX, + FLT_MAX); + }; + for (int64_t batch_idx = 0; batch_idx < ne12; ++batch_idx) { const uint8_t * lhs_batch_base = static_cast(src1->data) + batch_idx * src1->nb[2]; uint8_t * dst_batch_base = static_cast(dst->data) + batch_idx * dst->nb[2]; if (runtime[local_slot].assigned_threads > 0) { runtime_slot & slot = runtime[local_slot]; - const ggml_type slot_rhs_type = slot.kernels->rhs_type; - const size_t slot_lhs_exec_arg = slot_rhs_type == GGML_TYPE_Q4_0 ? QK4_0 : - slot_rhs_type == GGML_TYPE_Q8_0 ? 0 : 0; const int64_t m_roundup_mr = kai_roundup((int64_t)m, (int64_t)slot.mr); int64_t max_threads = slot.mr ? (m_roundup_mr / (int64_t)slot.mr) : slot.assigned_threads; max_threads = std::max(1, max_threads); @@ -1031,8 +1061,8 @@ class tensor_traits : public ggml::cpu::tensor_traits { const int64_t m_start = (int64_t)local_ith * num_m_per_thread0; const int64_t m_count = (local_ith == use_threads - 1) ? num_m_per_threadN_1 : num_m_per_thread0; - const size_t base_packed_off = slot.lhs_info->get_packed_offset_ex(m_start, k, slot_lhs_exec_arg, slot.mr, slot.kr, slot.sr); - const size_t next_block_off = slot.lhs_info->get_packed_offset_ex(m_start + slot.mr, k, slot_lhs_exec_arg, slot.mr, slot.kr, slot.sr); + const size_t base_packed_off = slot.lhs_info->get_packed_offset_ex(m_start, k, slot.lhs_bl, slot.mr, slot.kr, slot.sr); + const size_t next_block_off = slot.lhs_info->get_packed_offset_ex(m_start + slot.mr, k, slot.lhs_bl, slot.mr, slot.kr, slot.sr); const size_t row_stride_bytes = slot.mr ? (next_block_off - base_packed_off) / slot.mr : 0; int64_t remaining = m_count; @@ -1049,7 +1079,7 @@ class tensor_traits : public ggml::cpu::tensor_traits { const size_t dst_off = base_packed_off + (size_t)(cur - m_start) * row_stride_bytes; void * dst_ptr = lhs_packed + dst_off; - slot.lhs_info->pack_func_ex(take, k, slot_lhs_exec_arg, slot.mr, slot.kr, slot.sr, 0, src_ptr, src1->nb[1], dst_ptr); + slot.lhs_info->pack_func_ex(take, k, slot.lhs_bl, slot.mr, slot.kr, slot.sr, 0, src_ptr, src1->nb[1], dst_ptr); cur += take; remaining -= take; @@ -1057,49 +1087,29 @@ class tensor_traits : public ggml::cpu::tensor_traits { } } + if (ith_total == 0) { + ggml_threadpool_chunk_set(params->threadpool, nth_total); + } + + // Publishes both LHS packing and the initialized dynamic chunk queue. ggml_barrier(params->threadpool); runtime_slot & slot = runtime[local_slot]; - if (slot.n_cols > 0 && slot.assigned_threads > 0) { - int64_t active_threads = slot.assigned_threads; - const int64_t max_threads = slot.n_step ? (slot.n_cols / slot.n_step) : slot.assigned_threads; - if (max_threads > 0) { - active_threads = std::min(active_threads, std::max(1, max_threads)); + int current_chunk = ith_total; + while (current_chunk < nchunk) { + const size_t global_start = (size_t)current_chunk * chunk_cols; + if (global_start >= n) { + break; } - active_threads = std::max(1, active_threads); - - if (local_ith < active_threads) { - const size_t step = slot.n_step ? slot.n_step : 1; - const size_t chunk0 = round_down((size_t)(slot.n_cols / active_threads), step); - const size_t chunkN = slot.n_cols - (active_threads - 1) * chunk0; - const size_t local_start = (size_t)local_ith * chunk0; - const size_t cols = (local_ith == active_threads - 1) ? chunkN : chunk0; - - if (cols > 0) { - const ggml_type slot_rhs_type = slot.kernels->rhs_type; - const size_t slot_lhs_exec_arg = slot_rhs_type == GGML_TYPE_Q4_0 ? QK4_0 : - slot_rhs_type == GGML_TYPE_Q8_0 ? 0 : 0; - const size_t slot_rhs_block_arg = slot_rhs_type == GGML_TYPE_Q4_0 ? QK4_0 : - slot_rhs_type == GGML_TYPE_Q8_0 ? 0 : 0; - const size_t global_start = slot.n_offset + local_start; - const size_t lhs_packed_offset = slot.lhs_info->get_packed_offset_ex(0, k, slot_lhs_exec_arg, slot.mr, slot.kr, slot.sr); - const size_t rhs_packed_offset = slot.kernel->get_rhs_packed_offset_ex(global_start, k, slot_rhs_block_arg); - const size_t dst_offset = slot.kernel->get_dst_offset(0, global_start, dst_stride); - - const uint8_t * lhs_ptr = scratch + slot.lhs_offset + lhs_packed_offset; - const uint8_t * rhs_ptr = slot.rhs_base + rhs_packed_offset; - float * dst_ptr = reinterpret_cast(dst_batch_base + dst_offset); - - slot.kernel->run_kernel_ex(m, cols, k, slot_rhs_block_arg, - lhs_ptr, - rhs_ptr, - dst_ptr, - dst_stride, - sizeof(float), - -FLT_MAX, - FLT_MAX); - } + + const size_t cols = std::min(chunk_cols, n - global_start); + if (cols > 0) { + // KleidiAI GEMM/GEMV kernels accept arbitrary final tail widths; + // only non-tail chunks are guaranteed to be n_step-aligned. + run_chunk(slot, global_start, cols, dst_batch_base); } + + current_chunk = ggml_threadpool_chunk_add(params->threadpool, 1); } if (batch_idx != ne12 - 1) { diff --git a/ggml/src/ggml-cuda/mmvq.cu b/ggml/src/ggml-cuda/mmvq.cu index 4b0426590acc..bdfbfd2d387f 100644 --- a/ggml/src/ggml-cuda/mmvq.cu +++ b/ggml/src/ggml-cuda/mmvq.cu @@ -682,12 +682,16 @@ static __global__ void mul_mat_vec_q( template __launch_bounds__(get_mmvq_mmid_max_batch_for_device()*ggml_cuda_get_physical_warp_size(), 1) static __global__ void mul_mat_vec_q_moe( - const void * __restrict__ vx, const void * __restrict__ vy, const int32_t * __restrict__ ids, - float * __restrict__ dst, + const void * vx_ptr, const void * vy_ptr, const int32_t * ids_ptr, + float * dst_ptr, const uint32_t ncols_x, const uint3 nchannels_y, const uint32_t nrows_x, const uint32_t stride_row_x, const uint32_t stride_col_y, const uint32_t stride_col_dst, const uint32_t stride_channel_x, const uint32_t stride_channel_y, const uint32_t stride_channel_dst, const uint32_t ncols_dst, const uint32_t ids_stride) { + const void * GGML_CUDA_RESTRICT vx = vx_ptr; + const void * GGML_CUDA_RESTRICT vy = vy_ptr; + const int32_t * GGML_CUDA_RESTRICT ids = ids_ptr; + float * GGML_CUDA_RESTRICT dst = dst_ptr; constexpr int qk = ggml_cuda_type_traits::qk; constexpr int qi = ggml_cuda_type_traits::qi; @@ -707,6 +711,7 @@ static __global__ void mul_mat_vec_q_moe( return; } + ggml_cuda_pdl_sync(); const uint32_t channel_x = ids[channel_dst + token_idx * ids_stride]; const uint32_t channel_y = fastmodulo(channel_dst, nchannels_y); @@ -726,6 +731,8 @@ static __global__ void mul_mat_vec_q_moe( } } + ggml_cuda_pdl_lc(); + // Warp-level reduction only - no shared memory needed #pragma unroll for (int i = 0; i < c_rows_per_block; ++i) { @@ -794,8 +801,9 @@ static void mul_mat_vec_q_moe_launch( const int64_t nblocks_rows = (nrows_x + rows_per_block - 1) / rows_per_block; const dim3 block_nums(nblocks_rows, nchannels_dst); const dim3 block_dims(warp_size, ncols_dst); + const ggml_cuda_kernel_launch_params launch_params = ggml_cuda_kernel_launch_params(block_nums, block_dims, 0, stream); - mul_mat_vec_q_moe<<>>( + ggml_cuda_kernel_launch(mul_mat_vec_q_moe, launch_params, vx, vy, ids, dst, ncols_x, nchannels_y, nrows_x, stride_row_x, stride_col_y, stride_col_dst, stride_channel_x, stride_channel_y, stride_channel_dst, diff --git a/ggml/src/ggml-sycl/ggml-sycl.cpp b/ggml/src/ggml-sycl/ggml-sycl.cpp index 96138f57ebe6..3f246e8672d5 100644 --- a/ggml/src/ggml-sycl/ggml-sycl.cpp +++ b/ggml/src/ggml-sycl/ggml-sycl.cpp @@ -3971,7 +3971,9 @@ static bool should_reorder_tensor(ggml_backend_sycl_context& ctx, const ggml_ten return !g_ggml_sycl_disable_optimize && //allow optimize, controlled by $GGML_SYCL_DISABLE_OPT ctx.opt_feature.reorder && //allow this device due to good perf, skip the devices with bad perf. dst->op == GGML_OP_MUL_MAT && //limit to some supported cases of Q4_0, to do for more cases. - dst->src[1]->ne[1]==1 && dst->src[1]->ne[2]==1 && dst->src[1]->ne[3]==1; + // ne[1] <= 8 so multi-column decode (spec / MTP verify) also bootstraps the reorder; + // all reorderable types have a _switch_ncols kernel. + dst->src[1]->ne[1] <= 8 && dst->src[1]->ne[2]==1 && dst->src[1]->ne[3]==1; } static void opt_for_reorder(ggml_backend_sycl_context * ctx, const ggml_tensor * src0, const ggml_tensor * /* src1 */, diff --git a/ggml/src/ggml-sycl/mmvq.cpp b/ggml/src/ggml-sycl/mmvq.cpp index abd1e49a70e6..cf2b59576aa1 100644 --- a/ggml/src/ggml-sycl/mmvq.cpp +++ b/ggml/src/ggml-sycl/mmvq.cpp @@ -56,6 +56,65 @@ static void mul_mat_vec_q_reorder(const void * __restrict__ vx, const void * __r } } +template +static void mul_mat_vec_q_reorder_ncols(const void * __restrict__ vx, const void * __restrict__ vy, + float * __restrict__ dst, const int ncols, const int nrows, + const int stride_col_y_bytes, const int stride_col_dst, + const sycl::nd_item<3> & nd_item) { + using block_type = ggml_sycl_reordered::block_q_t; + using block_traits = typename block_type::traits; + + const auto sg = nd_item.get_sub_group(); + const int sg_range = sg.get_group_linear_range(); + const int workgroup_id = nd_item.get_group_linear_id(); + const int sg_id = sg.get_group_linear_id(); + const int row = workgroup_id * sg_range + sg_id; + + if (row >= nrows) { + return; + } + + const int blocks_per_row = ncols / block_traits::qk; + constexpr int blocks_per_subgroup = ceil_div(block_traits::vdr_mmvq * WARP_SIZE, block_traits::qi); + constexpr int block_elements_per_subgroup = block_traits::qi / block_traits::vdr_mmvq; + const int nblocks = nrows * (ncols / block_traits::qk); + + static_assert(blocks_per_subgroup > 0); + static_assert(block_elements_per_subgroup > 0); + + float partial_sum[ncols_dst] = {0.0f}; + for (int i = sg.get_local_linear_id() / block_elements_per_subgroup; i < blocks_per_row; i += blocks_per_subgroup) { + const int ibx = row * blocks_per_row + i; + + const auto bx_offset = block_type::get_block_offset(ibx, nblocks); + const auto d_offset = block_type::get_d_offset(nrows, ncols, ibx); + const int iby = i * block_type::block_to_q8_1_ratio(); + +#pragma unroll + for (int elem = 0; elem < block_elements_per_subgroup; elem += WARP_SIZE) { + const int iqs = elem + block_traits::vdr_mmvq * (sg.get_local_linear_id() % block_elements_per_subgroup); + +#pragma unroll + for (int j = 0; j < ncols_dst; ++j) { + const char * vy_j = (const char *)vy + j * stride_col_y_bytes; + const int8_t * q8_1_quant_ptr = (const int8_t *)vy_j + iby * QK8_1; + const sycl::half2* q8_1_ds_ptr = (const sycl::half2 *)(vy_j + ncols + iby * sizeof(sycl::half2)); + + partial_sum[j] += reorder_vec_dot_q_sycl()(vx, bx_offset, d_offset, q8_1_quant_ptr, q8_1_ds_ptr, iqs); + } + } + } + +#pragma unroll + for (int j = 0; j < ncols_dst; ++j) { + float sum = sycl::reduce_over_group(nd_item.get_sub_group(), partial_sum[j], std::plus<>()); + + if (sg.leader()) { + dst[j * stride_col_dst + row] = sum; + } + } +} + template static void mul_mat_vec_q(const void * __restrict__ vx, const void * __restrict__ vy, float * __restrict__ dst, const int ncols, const int nrows, const sycl::nd_item<3> & item_ct1) { @@ -100,6 +159,70 @@ static void mul_mat_vec_q(const void * __restrict__ vx, const void * __restrict_ } } +template +static void mul_mat_vec_q_ncols( + const void * __restrict__ vx, + const void * __restrict__ vy, + float * __restrict__ dst, + const int ncols, + const int nrows, + const int stride_col_y, + const int stride_col_dst, + const sycl::nd_item<3> & item_ct1) { + + const int row = item_ct1.get_group(2) * item_ct1.get_local_range(1) + + item_ct1.get_local_id(1); + + if (row >= nrows) { + return; + } + + const int blocks_per_row = ncols / qk; + constexpr int blocks_per_warp = (vdr * WARP_SIZE + qi - 1) / qi; + + // partial sums: one per output column + float tmp[ncols_dst] = {0.0f}; + + const block_q_t * x = (const block_q_t *) vx; + const block_q8_1 * y = (const block_q8_1 *) vy; + + for (int i = item_ct1.get_local_id(2) / (qi / vdr); + i < blocks_per_row; + i += blocks_per_warp) { + + const int ibx = row * blocks_per_row + i; + const int iby = i * (qk / QK8_1); + + // read weight block once, dot against all columns + for (size_t elem = 0; elem < qi / vdr; elem += WARP_SIZE) { + const int iqs = elem + vdr * (item_ct1.get_local_id(2) % (qi / vdr)); + +#pragma unroll + for (int j = 0; j < ncols_dst; ++j) { + tmp[j] += vec_dot_q_sycl(&x[ibx], &y[j * stride_col_y + iby], iqs); + } + } + } + + // reduce within subgroup +#pragma unroll + for (int j = 0; j < ncols_dst; ++j) { +#pragma unroll + for (int mask = WARP_SIZE / 2; mask > 0; mask >>= 1) { + tmp[j] += dpct::permute_sub_group_by_xor( + item_ct1.get_sub_group(), tmp[j], mask); + } + } + + if (item_ct1.get_local_id(2) == 0) { +#pragma unroll + for (int j = 0; j < ncols_dst; ++j) { + dst[j * stride_col_dst + row] = tmp[j]; + } + } +} + template static void mul_mat_vec_q_iq2_xxs_q8_1(const void *__restrict__ vx, const void *__restrict__ vy, @@ -553,6 +676,45 @@ static void reorder_mul_mat_vec_q4_0_q8_1_sycl(const void * vx, const void * vy, }); } +template +static void reorder_mul_mat_vec_q4_0_q8_1_sycl_ncols( + const void * vx, const void * vy, float * dst, + const int ncols, const int nrows, + const int stride_col_y_bytes, const int stride_col_dst, + dpct::queue_ptr stream) { + GGML_ASSERT(ncols % QK4_0 == 0); + const int block_num_y = ceil_div(nrows, GGML_SYCL_MMV_Y); + constexpr size_t num_subgroups = 16; + GGML_ASSERT(block_num_y % num_subgroups == 0); + const sycl::range<3> global_size(1, GGML_SYCL_MMV_Y, block_num_y * WARP_SIZE); + const sycl::range<3> workgroup_size(1, GGML_SYCL_MMV_Y, num_subgroups * WARP_SIZE); + stream->submit([&](sycl::handler & cgh) { + cgh.parallel_for(sycl::nd_range<3>(global_size, workgroup_size), + [=](sycl::nd_item<3> nd_item) [[sycl::reqd_sub_group_size(WARP_SIZE)]] { + mul_mat_vec_q_reorder_ncols, ncols_dst>( + vx, vy, dst, ncols, nrows, stride_col_y_bytes, stride_col_dst, nd_item); + }); + }); +} + +static void reorder_mul_mat_vec_q4_0_q8_1_sycl_switch_ncols( + const void * vx, const void * vy, float * dst, + const int ncols, const int nrows, const int ncols_dst, + const int stride_col_y_bytes, const int stride_col_dst, + dpct::queue_ptr stream) { + switch (ncols_dst) { + case 1: reorder_mul_mat_vec_q4_0_q8_1_sycl(vx, vy, dst, ncols, nrows, stream); break; + case 2: reorder_mul_mat_vec_q4_0_q8_1_sycl_ncols<2>(vx, vy, dst, ncols, nrows, stride_col_y_bytes, stride_col_dst, stream); break; + case 3: reorder_mul_mat_vec_q4_0_q8_1_sycl_ncols<3>(vx, vy, dst, ncols, nrows, stride_col_y_bytes, stride_col_dst, stream); break; + case 4: reorder_mul_mat_vec_q4_0_q8_1_sycl_ncols<4>(vx, vy, dst, ncols, nrows, stride_col_y_bytes, stride_col_dst, stream); break; + case 5: reorder_mul_mat_vec_q4_0_q8_1_sycl_ncols<5>(vx, vy, dst, ncols, nrows, stride_col_y_bytes, stride_col_dst, stream); break; + case 6: reorder_mul_mat_vec_q4_0_q8_1_sycl_ncols<6>(vx, vy, dst, ncols, nrows, stride_col_y_bytes, stride_col_dst, stream); break; + case 7: reorder_mul_mat_vec_q4_0_q8_1_sycl_ncols<7>(vx, vy, dst, ncols, nrows, stride_col_y_bytes, stride_col_dst, stream); break; + case 8: reorder_mul_mat_vec_q4_0_q8_1_sycl_ncols<8>(vx, vy, dst, ncols, nrows, stride_col_y_bytes, stride_col_dst, stream); break; + default: GGML_ABORT("unsupported ncols_dst=%d for Q4_0 reorder multi-col MMVQ", ncols_dst); + } +} + static void mul_mat_vec_q4_0_q8_1_sycl(const void * vx, const void * vy, float * dst, const int ncols, const int nrows, dpct::queue_ptr stream) { GGML_ASSERT(ncols % QK4_0 == 0); @@ -571,6 +733,45 @@ static void mul_mat_vec_q4_0_q8_1_sycl(const void * vx, const void * vy, float * } } +template +static void mul_mat_vec_q4_0_q8_1_sycl_ncols( + const void * vx, const void * vy, float * dst, + const int ncols, const int nrows, + const int stride_col_y, const int stride_col_dst, + dpct::queue_ptr stream) { + GGML_ASSERT(ncols % QK4_0 == 0); + const int block_num_y = (nrows + GGML_SYCL_MMV_Y - 1) / GGML_SYCL_MMV_Y; + const sycl::range<3> block_nums(1, 1, block_num_y); + const sycl::range<3> block_dims(1, GGML_SYCL_MMV_Y, WARP_SIZE); + stream->submit([&](sycl::handler & cgh) { + cgh.parallel_for( + sycl::nd_range<3>(block_nums * block_dims, block_dims), + [=](sycl::nd_item<3> item_ct1) [[sycl::reqd_sub_group_size(WARP_SIZE)]] { + mul_mat_vec_q_ncols( + vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, item_ct1); + }); + }); +} + +static void mul_mat_vec_q4_0_q8_1_sycl_switch_ncols( + const void * vx, const void * vy, float * dst, + const int ncols, const int nrows, const int ncols_dst, + const int stride_col_y, const int stride_col_dst, + dpct::queue_ptr stream) { + switch (ncols_dst) { + case 1: mul_mat_vec_q4_0_q8_1_sycl(vx, vy, dst, ncols, nrows, stream); break; + case 2: mul_mat_vec_q4_0_q8_1_sycl_ncols<2>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 3: mul_mat_vec_q4_0_q8_1_sycl_ncols<3>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 4: mul_mat_vec_q4_0_q8_1_sycl_ncols<4>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 5: mul_mat_vec_q4_0_q8_1_sycl_ncols<5>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 6: mul_mat_vec_q4_0_q8_1_sycl_ncols<6>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 7: mul_mat_vec_q4_0_q8_1_sycl_ncols<7>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 8: mul_mat_vec_q4_0_q8_1_sycl_ncols<8>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + default: GGML_ABORT("unsupported ncols_dst=%d for Q4_0 multi-col MMVQ", ncols_dst); + } +} + static void mul_mat_vec_q4_1_q8_1_sycl(const void *vx, const void *vy, float *dst, const int ncols, const int nrows, @@ -595,6 +796,45 @@ static void mul_mat_vec_q4_1_q8_1_sycl(const void *vx, const void *vy, } } +template +static void mul_mat_vec_q4_1_q8_1_sycl_ncols( + const void * vx, const void * vy, float * dst, + const int ncols, const int nrows, + const int stride_col_y, const int stride_col_dst, + dpct::queue_ptr stream) { + GGML_ASSERT(ncols % QK4_1 == 0); + const int block_num_y = (nrows + GGML_SYCL_MMV_Y - 1) / GGML_SYCL_MMV_Y; + const sycl::range<3> block_nums(1, 1, block_num_y); + const sycl::range<3> block_dims(1, GGML_SYCL_MMV_Y, WARP_SIZE); + stream->submit([&](sycl::handler & cgh) { + cgh.parallel_for( + sycl::nd_range<3>(block_nums * block_dims, block_dims), + [=](sycl::nd_item<3> item_ct1) [[sycl::reqd_sub_group_size(WARP_SIZE)]] { + mul_mat_vec_q_ncols( + vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, item_ct1); + }); + }); +} + +static void mul_mat_vec_q4_1_q8_1_sycl_switch_ncols( + const void * vx, const void * vy, float * dst, + const int ncols, const int nrows, const int ncols_dst, + const int stride_col_y, const int stride_col_dst, + dpct::queue_ptr stream) { + switch (ncols_dst) { + case 1: mul_mat_vec_q4_1_q8_1_sycl(vx, vy, dst, ncols, nrows, stream); break; + case 2: mul_mat_vec_q4_1_q8_1_sycl_ncols<2>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 3: mul_mat_vec_q4_1_q8_1_sycl_ncols<3>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 4: mul_mat_vec_q4_1_q8_1_sycl_ncols<4>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 5: mul_mat_vec_q4_1_q8_1_sycl_ncols<5>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 6: mul_mat_vec_q4_1_q8_1_sycl_ncols<6>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 7: mul_mat_vec_q4_1_q8_1_sycl_ncols<7>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 8: mul_mat_vec_q4_1_q8_1_sycl_ncols<8>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + default: GGML_ABORT("unsupported ncols_dst=%d for Q4_1 multi-col MMVQ", ncols_dst); + } +} + static void mul_mat_vec_mxfp4_q8_1_sycl(const void * vx, const void * vy, float * dst, const int ncols, const int nrows, dpct::queue_ptr stream) { GGML_ASSERT(ncols % QK_MXFP4 == 0); @@ -613,6 +853,45 @@ static void mul_mat_vec_mxfp4_q8_1_sycl(const void * vx, const void * vy, float } } +template +static void mul_mat_vec_mxfp4_q8_1_sycl_ncols( + const void * vx, const void * vy, float * dst, + const int ncols, const int nrows, + const int stride_col_y, const int stride_col_dst, + dpct::queue_ptr stream) { + GGML_ASSERT(ncols % QK_MXFP4 == 0); + const int block_num_y = (nrows + GGML_SYCL_MMV_Y - 1) / GGML_SYCL_MMV_Y; + const sycl::range<3> block_nums(1, 1, block_num_y); + const sycl::range<3> block_dims(1, GGML_SYCL_MMV_Y, WARP_SIZE); + stream->submit([&](sycl::handler & cgh) { + cgh.parallel_for( + sycl::nd_range<3>(block_nums * block_dims, block_dims), + [=](sycl::nd_item<3> item_ct1) [[sycl::reqd_sub_group_size(WARP_SIZE)]] { + mul_mat_vec_q_ncols( + vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, item_ct1); + }); + }); +} + +static void mul_mat_vec_mxfp4_q8_1_sycl_switch_ncols( + const void * vx, const void * vy, float * dst, + const int ncols, const int nrows, const int ncols_dst, + const int stride_col_y, const int stride_col_dst, + dpct::queue_ptr stream) { + switch (ncols_dst) { + case 1: mul_mat_vec_mxfp4_q8_1_sycl(vx, vy, dst, ncols, nrows, stream); break; + case 2: mul_mat_vec_mxfp4_q8_1_sycl_ncols<2>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 3: mul_mat_vec_mxfp4_q8_1_sycl_ncols<3>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 4: mul_mat_vec_mxfp4_q8_1_sycl_ncols<4>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 5: mul_mat_vec_mxfp4_q8_1_sycl_ncols<5>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 6: mul_mat_vec_mxfp4_q8_1_sycl_ncols<6>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 7: mul_mat_vec_mxfp4_q8_1_sycl_ncols<7>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 8: mul_mat_vec_mxfp4_q8_1_sycl_ncols<8>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + default: GGML_ABORT("unsupported ncols_dst=%d for MXFP4 multi-col MMVQ", ncols_dst); + } +} + static void mul_mat_vec_nvfp4_q8_1_sycl(const void * vx, const void * vy, float * dst, const int ncols, const int nrows, dpct::queue_ptr stream) { GGML_ASSERT(ncols % QK_NVFP4 == 0); @@ -631,6 +910,45 @@ static void mul_mat_vec_nvfp4_q8_1_sycl(const void * vx, const void * vy, float } } +template +static void mul_mat_vec_nvfp4_q8_1_sycl_ncols( + const void * vx, const void * vy, float * dst, + const int ncols, const int nrows, + const int stride_col_y, const int stride_col_dst, + dpct::queue_ptr stream) { + GGML_ASSERT(ncols % QK_NVFP4 == 0); + const int block_num_y = (nrows + GGML_SYCL_MMV_Y - 1) / GGML_SYCL_MMV_Y; + const sycl::range<3> block_nums(1, 1, block_num_y); + const sycl::range<3> block_dims(1, GGML_SYCL_MMV_Y, WARP_SIZE); + stream->submit([&](sycl::handler & cgh) { + cgh.parallel_for( + sycl::nd_range<3>(block_nums * block_dims, block_dims), + [=](sycl::nd_item<3> item_ct1) [[sycl::reqd_sub_group_size(WARP_SIZE)]] { + mul_mat_vec_q_ncols( + vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, item_ct1); + }); + }); +} + +static void mul_mat_vec_nvfp4_q8_1_sycl_switch_ncols( + const void * vx, const void * vy, float * dst, + const int ncols, const int nrows, const int ncols_dst, + const int stride_col_y, const int stride_col_dst, + dpct::queue_ptr stream) { + switch (ncols_dst) { + case 1: mul_mat_vec_nvfp4_q8_1_sycl(vx, vy, dst, ncols, nrows, stream); break; + case 2: mul_mat_vec_nvfp4_q8_1_sycl_ncols<2>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 3: mul_mat_vec_nvfp4_q8_1_sycl_ncols<3>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 4: mul_mat_vec_nvfp4_q8_1_sycl_ncols<4>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 5: mul_mat_vec_nvfp4_q8_1_sycl_ncols<5>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 6: mul_mat_vec_nvfp4_q8_1_sycl_ncols<6>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 7: mul_mat_vec_nvfp4_q8_1_sycl_ncols<7>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 8: mul_mat_vec_nvfp4_q8_1_sycl_ncols<8>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + default: GGML_ABORT("unsupported ncols_dst=%d for NVFP4 multi-col MMVQ", ncols_dst); + } +} + static void mul_mat_vec_q5_0_q8_1_sycl(const void *vx, const void *vy, float *dst, const int ncols, const int nrows, @@ -655,6 +973,45 @@ static void mul_mat_vec_q5_0_q8_1_sycl(const void *vx, const void *vy, } } +template +static void mul_mat_vec_q5_0_q8_1_sycl_ncols( + const void * vx, const void * vy, float * dst, + const int ncols, const int nrows, + const int stride_col_y, const int stride_col_dst, + dpct::queue_ptr stream) { + GGML_ASSERT(ncols % QK5_0 == 0); + const int block_num_y = (nrows + GGML_SYCL_MMV_Y - 1) / GGML_SYCL_MMV_Y; + const sycl::range<3> block_nums(1, 1, block_num_y); + const sycl::range<3> block_dims(1, GGML_SYCL_MMV_Y, WARP_SIZE); + stream->submit([&](sycl::handler & cgh) { + cgh.parallel_for( + sycl::nd_range<3>(block_nums * block_dims, block_dims), + [=](sycl::nd_item<3> item_ct1) [[sycl::reqd_sub_group_size(WARP_SIZE)]] { + mul_mat_vec_q_ncols( + vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, item_ct1); + }); + }); +} + +static void mul_mat_vec_q5_0_q8_1_sycl_switch_ncols( + const void * vx, const void * vy, float * dst, + const int ncols, const int nrows, const int ncols_dst, + const int stride_col_y, const int stride_col_dst, + dpct::queue_ptr stream) { + switch (ncols_dst) { + case 1: mul_mat_vec_q5_0_q8_1_sycl(vx, vy, dst, ncols, nrows, stream); break; + case 2: mul_mat_vec_q5_0_q8_1_sycl_ncols<2>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 3: mul_mat_vec_q5_0_q8_1_sycl_ncols<3>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 4: mul_mat_vec_q5_0_q8_1_sycl_ncols<4>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 5: mul_mat_vec_q5_0_q8_1_sycl_ncols<5>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 6: mul_mat_vec_q5_0_q8_1_sycl_ncols<6>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 7: mul_mat_vec_q5_0_q8_1_sycl_ncols<7>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 8: mul_mat_vec_q5_0_q8_1_sycl_ncols<8>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + default: GGML_ABORT("unsupported ncols_dst=%d for Q5_0 multi-col MMVQ", ncols_dst); + } +} + static void mul_mat_vec_q5_1_q8_1_sycl(const void *vx, const void *vy, float *dst, const int ncols, const int nrows, @@ -679,6 +1036,45 @@ static void mul_mat_vec_q5_1_q8_1_sycl(const void *vx, const void *vy, } } +template +static void mul_mat_vec_q5_1_q8_1_sycl_ncols( + const void * vx, const void * vy, float * dst, + const int ncols, const int nrows, + const int stride_col_y, const int stride_col_dst, + dpct::queue_ptr stream) { + GGML_ASSERT(ncols % QK5_1 == 0); + const int block_num_y = (nrows + GGML_SYCL_MMV_Y - 1) / GGML_SYCL_MMV_Y; + const sycl::range<3> block_nums(1, 1, block_num_y); + const sycl::range<3> block_dims(1, GGML_SYCL_MMV_Y, WARP_SIZE); + stream->submit([&](sycl::handler & cgh) { + cgh.parallel_for( + sycl::nd_range<3>(block_nums * block_dims, block_dims), + [=](sycl::nd_item<3> item_ct1) [[sycl::reqd_sub_group_size(WARP_SIZE)]] { + mul_mat_vec_q_ncols( + vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, item_ct1); + }); + }); +} + +static void mul_mat_vec_q5_1_q8_1_sycl_switch_ncols( + const void * vx, const void * vy, float * dst, + const int ncols, const int nrows, const int ncols_dst, + const int stride_col_y, const int stride_col_dst, + dpct::queue_ptr stream) { + switch (ncols_dst) { + case 1: mul_mat_vec_q5_1_q8_1_sycl(vx, vy, dst, ncols, nrows, stream); break; + case 2: mul_mat_vec_q5_1_q8_1_sycl_ncols<2>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 3: mul_mat_vec_q5_1_q8_1_sycl_ncols<3>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 4: mul_mat_vec_q5_1_q8_1_sycl_ncols<4>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 5: mul_mat_vec_q5_1_q8_1_sycl_ncols<5>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 6: mul_mat_vec_q5_1_q8_1_sycl_ncols<6>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 7: mul_mat_vec_q5_1_q8_1_sycl_ncols<7>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 8: mul_mat_vec_q5_1_q8_1_sycl_ncols<8>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + default: GGML_ABORT("unsupported ncols_dst=%d for Q5_1 multi-col MMVQ", ncols_dst); + } +} + static void reorder_mul_mat_vec_q8_0_q8_1_sycl(const void * vx, const void * vy, float * dst, const int ncols, const int nrows, dpct::queue_ptr stream) { GGML_ASSERT(ncols % QK8_0 == 0); @@ -698,6 +1094,45 @@ static void reorder_mul_mat_vec_q8_0_q8_1_sycl(const void * vx, const void * vy, }); } +template +static void reorder_mul_mat_vec_q8_0_q8_1_sycl_ncols( + const void * vx, const void * vy, float * dst, + const int ncols, const int nrows, + const int stride_col_y_bytes, const int stride_col_dst, + dpct::queue_ptr stream) { + GGML_ASSERT(ncols % QK8_0 == 0); + const int block_num_y = ceil_div(nrows, GGML_SYCL_MMV_Y); + constexpr size_t num_subgroups = 16; + GGML_ASSERT(block_num_y % num_subgroups == 0); + const sycl::range<3> global_size(1, GGML_SYCL_MMV_Y, block_num_y * WARP_SIZE); + const sycl::range<3> workgroup_size(1, GGML_SYCL_MMV_Y, num_subgroups * WARP_SIZE); + stream->submit([&](sycl::handler & cgh) { + cgh.parallel_for(sycl::nd_range<3>(global_size, workgroup_size), + [=](sycl::nd_item<3> nd_item) [[sycl::reqd_sub_group_size(WARP_SIZE)]] { + mul_mat_vec_q_reorder_ncols, ncols_dst>( + vx, vy, dst, ncols, nrows, stride_col_y_bytes, stride_col_dst, nd_item); + }); + }); +} + +static void reorder_mul_mat_vec_q8_0_q8_1_sycl_switch_ncols( + const void * vx, const void * vy, float * dst, + const int ncols, const int nrows, const int ncols_dst, + const int stride_col_y_bytes, const int stride_col_dst, + dpct::queue_ptr stream) { + switch (ncols_dst) { + case 1: reorder_mul_mat_vec_q8_0_q8_1_sycl(vx, vy, dst, ncols, nrows, stream); break; + case 2: reorder_mul_mat_vec_q8_0_q8_1_sycl_ncols<2>(vx, vy, dst, ncols, nrows, stride_col_y_bytes, stride_col_dst, stream); break; + case 3: reorder_mul_mat_vec_q8_0_q8_1_sycl_ncols<3>(vx, vy, dst, ncols, nrows, stride_col_y_bytes, stride_col_dst, stream); break; + case 4: reorder_mul_mat_vec_q8_0_q8_1_sycl_ncols<4>(vx, vy, dst, ncols, nrows, stride_col_y_bytes, stride_col_dst, stream); break; + case 5: reorder_mul_mat_vec_q8_0_q8_1_sycl_ncols<5>(vx, vy, dst, ncols, nrows, stride_col_y_bytes, stride_col_dst, stream); break; + case 6: reorder_mul_mat_vec_q8_0_q8_1_sycl_ncols<6>(vx, vy, dst, ncols, nrows, stride_col_y_bytes, stride_col_dst, stream); break; + case 7: reorder_mul_mat_vec_q8_0_q8_1_sycl_ncols<7>(vx, vy, dst, ncols, nrows, stride_col_y_bytes, stride_col_dst, stream); break; + case 8: reorder_mul_mat_vec_q8_0_q8_1_sycl_ncols<8>(vx, vy, dst, ncols, nrows, stride_col_y_bytes, stride_col_dst, stream); break; + default: GGML_ABORT("unsupported ncols_dst=%d for Q8_0 reorder multi-col MMVQ", ncols_dst); + } +} + static void mul_mat_vec_q8_0_q8_1_sycl(const void *vx, const void *vy, float *dst, const int ncols, const int nrows, @@ -722,6 +1157,45 @@ static void mul_mat_vec_q8_0_q8_1_sycl(const void *vx, const void *vy, } } +template +static void mul_mat_vec_q8_0_q8_1_sycl_ncols( + const void * vx, const void * vy, float * dst, + const int ncols, const int nrows, + const int stride_col_y, const int stride_col_dst, + dpct::queue_ptr stream) { + GGML_ASSERT(ncols % QK8_0 == 0); + const int block_num_y = (nrows + GGML_SYCL_MMV_Y - 1) / GGML_SYCL_MMV_Y; + const sycl::range<3> block_nums(1, 1, block_num_y); + const sycl::range<3> block_dims(1, GGML_SYCL_MMV_Y, WARP_SIZE); + stream->submit([&](sycl::handler & cgh) { + cgh.parallel_for( + sycl::nd_range<3>(block_nums * block_dims, block_dims), + [=](sycl::nd_item<3> item_ct1) [[sycl::reqd_sub_group_size(WARP_SIZE)]] { + mul_mat_vec_q_ncols( + vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, item_ct1); + }); + }); +} + +static void mul_mat_vec_q8_0_q8_1_sycl_switch_ncols( + const void * vx, const void * vy, float * dst, + const int ncols, const int nrows, const int ncols_dst, + const int stride_col_y, const int stride_col_dst, + dpct::queue_ptr stream) { + switch (ncols_dst) { + case 1: mul_mat_vec_q8_0_q8_1_sycl(vx, vy, dst, ncols, nrows, stream); break; + case 2: mul_mat_vec_q8_0_q8_1_sycl_ncols<2>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 3: mul_mat_vec_q8_0_q8_1_sycl_ncols<3>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 4: mul_mat_vec_q8_0_q8_1_sycl_ncols<4>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 5: mul_mat_vec_q8_0_q8_1_sycl_ncols<5>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 6: mul_mat_vec_q8_0_q8_1_sycl_ncols<6>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 7: mul_mat_vec_q8_0_q8_1_sycl_ncols<7>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 8: mul_mat_vec_q8_0_q8_1_sycl_ncols<8>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + default: GGML_ABORT("unsupported ncols_dst=%d for Q8_0 multi-col MMVQ", ncols_dst); + } +} + static void mul_mat_vec_q2_K_q8_1_sycl(const void *vx, const void *vy, float *dst, const int ncols, const int nrows, @@ -746,6 +1220,45 @@ static void mul_mat_vec_q2_K_q8_1_sycl(const void *vx, const void *vy, } } +template +static void mul_mat_vec_q2_K_q8_1_sycl_ncols( + const void * vx, const void * vy, float * dst, + const int ncols, const int nrows, + const int stride_col_y, const int stride_col_dst, + dpct::queue_ptr stream) { + GGML_ASSERT(ncols % QK_K == 0); + const int block_num_y = (nrows + GGML_SYCL_MMV_Y - 1) / GGML_SYCL_MMV_Y; + const sycl::range<3> block_nums(1, 1, block_num_y); + const sycl::range<3> block_dims(1, GGML_SYCL_MMV_Y, WARP_SIZE); + stream->submit([&](sycl::handler & cgh) { + cgh.parallel_for( + sycl::nd_range<3>(block_nums * block_dims, block_dims), + [=](sycl::nd_item<3> item_ct1) [[sycl::reqd_sub_group_size(WARP_SIZE)]] { + mul_mat_vec_q_ncols( + vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, item_ct1); + }); + }); +} + +static void mul_mat_vec_q2_K_q8_1_sycl_switch_ncols( + const void * vx, const void * vy, float * dst, + const int ncols, const int nrows, const int ncols_dst, + const int stride_col_y, const int stride_col_dst, + dpct::queue_ptr stream) { + switch (ncols_dst) { + case 1: mul_mat_vec_q2_K_q8_1_sycl(vx, vy, dst, ncols, nrows, stream); break; + case 2: mul_mat_vec_q2_K_q8_1_sycl_ncols<2>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 3: mul_mat_vec_q2_K_q8_1_sycl_ncols<3>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 4: mul_mat_vec_q2_K_q8_1_sycl_ncols<4>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 5: mul_mat_vec_q2_K_q8_1_sycl_ncols<5>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 6: mul_mat_vec_q2_K_q8_1_sycl_ncols<6>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 7: mul_mat_vec_q2_K_q8_1_sycl_ncols<7>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 8: mul_mat_vec_q2_K_q8_1_sycl_ncols<8>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + default: GGML_ABORT("unsupported ncols_dst=%d for Q2_K multi-col MMVQ", ncols_dst); + } +} + static void mul_mat_vec_q3_K_q8_1_sycl(const void *vx, const void *vy, float *dst, const int ncols, const int nrows, @@ -790,6 +1303,85 @@ static void reorder_mul_mat_vec_q3_k_q8_1_sycl(const void * vx, const void * vy, }); } +template +static void reorder_mul_mat_vec_q3_k_q8_1_sycl_ncols( + const void * vx, const void * vy, float * dst, + const int ncols, const int nrows, + const int stride_col_y_bytes, const int stride_col_dst, + dpct::queue_ptr stream) { + GGML_ASSERT(ncols % QK_K == 0); + const int block_num_y = ceil_div(nrows, GGML_SYCL_MMV_Y); + constexpr size_t num_subgroups = 16; + GGML_ASSERT(block_num_y % num_subgroups == 0); + const sycl::range<3> global_size(1, GGML_SYCL_MMV_Y, block_num_y * WARP_SIZE); + const sycl::range<3> workgroup_size(1, GGML_SYCL_MMV_Y, num_subgroups * WARP_SIZE); + stream->submit([&](sycl::handler & cgh) { + cgh.parallel_for(sycl::nd_range<3>(global_size, workgroup_size), + [=](sycl::nd_item<3> nd_item) [[sycl::reqd_sub_group_size(WARP_SIZE)]] { + mul_mat_vec_q_reorder_ncols, ncols_dst>( + vx, vy, dst, ncols, nrows, stride_col_y_bytes, stride_col_dst, nd_item); + }); + }); +} + +static void reorder_mul_mat_vec_q3_k_q8_1_sycl_switch_ncols( + const void * vx, const void * vy, float * dst, + const int ncols, const int nrows, const int ncols_dst, + const int stride_col_y_bytes, const int stride_col_dst, + dpct::queue_ptr stream) { + switch (ncols_dst) { + case 1: reorder_mul_mat_vec_q3_k_q8_1_sycl(vx, vy, dst, ncols, nrows, stream); break; + case 2: reorder_mul_mat_vec_q3_k_q8_1_sycl_ncols<2>(vx, vy, dst, ncols, nrows, stride_col_y_bytes, stride_col_dst, stream); break; + case 3: reorder_mul_mat_vec_q3_k_q8_1_sycl_ncols<3>(vx, vy, dst, ncols, nrows, stride_col_y_bytes, stride_col_dst, stream); break; + case 4: reorder_mul_mat_vec_q3_k_q8_1_sycl_ncols<4>(vx, vy, dst, ncols, nrows, stride_col_y_bytes, stride_col_dst, stream); break; + case 5: reorder_mul_mat_vec_q3_k_q8_1_sycl_ncols<5>(vx, vy, dst, ncols, nrows, stride_col_y_bytes, stride_col_dst, stream); break; + case 6: reorder_mul_mat_vec_q3_k_q8_1_sycl_ncols<6>(vx, vy, dst, ncols, nrows, stride_col_y_bytes, stride_col_dst, stream); break; + case 7: reorder_mul_mat_vec_q3_k_q8_1_sycl_ncols<7>(vx, vy, dst, ncols, nrows, stride_col_y_bytes, stride_col_dst, stream); break; + case 8: reorder_mul_mat_vec_q3_k_q8_1_sycl_ncols<8>(vx, vy, dst, ncols, nrows, stride_col_y_bytes, stride_col_dst, stream); break; + default: GGML_ABORT("unsupported ncols_dst=%d for Q3_K reorder multi-col MMVQ", ncols_dst); + } +} + +template +static void mul_mat_vec_q3_K_q8_1_sycl_ncols( + const void * vx, const void * vy, float * dst, + const int ncols, const int nrows, + const int stride_col_y, const int stride_col_dst, + dpct::queue_ptr stream) { + GGML_ASSERT(ncols % QK_K == 0); + const int block_num_y = (nrows + GGML_SYCL_MMV_Y - 1) / GGML_SYCL_MMV_Y; + const sycl::range<3> block_nums(1, 1, block_num_y); + const sycl::range<3> block_dims(1, GGML_SYCL_MMV_Y, WARP_SIZE); + stream->submit([&](sycl::handler & cgh) { + cgh.parallel_for( + sycl::nd_range<3>(block_nums * block_dims, block_dims), + [=](sycl::nd_item<3> item_ct1) [[sycl::reqd_sub_group_size(WARP_SIZE)]] { + mul_mat_vec_q_ncols( + vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, item_ct1); + }); + }); +} + +static void mul_mat_vec_q3_K_q8_1_sycl_switch_ncols( + const void * vx, const void * vy, float * dst, + const int ncols, const int nrows, const int ncols_dst, + const int stride_col_y, const int stride_col_dst, + dpct::queue_ptr stream) { + switch (ncols_dst) { + case 1: mul_mat_vec_q3_K_q8_1_sycl(vx, vy, dst, ncols, nrows, stream); break; + case 2: mul_mat_vec_q3_K_q8_1_sycl_ncols<2>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 3: mul_mat_vec_q3_K_q8_1_sycl_ncols<3>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 4: mul_mat_vec_q3_K_q8_1_sycl_ncols<4>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 5: mul_mat_vec_q3_K_q8_1_sycl_ncols<5>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 6: mul_mat_vec_q3_K_q8_1_sycl_ncols<6>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 7: mul_mat_vec_q3_K_q8_1_sycl_ncols<7>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 8: mul_mat_vec_q3_K_q8_1_sycl_ncols<8>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + default: GGML_ABORT("unsupported ncols_dst=%d for Q3_K multi-col MMVQ", ncols_dst); + } +} + + static void mul_mat_vec_q4_K_q8_1_sycl(const void *vx, const void *vy, float *dst, const int ncols, const int nrows, @@ -814,6 +1406,51 @@ static void mul_mat_vec_q4_K_q8_1_sycl(const void *vx, const void *vy, } } +template +static void mul_mat_vec_q4_K_q8_1_sycl_ncols( + const void * vx, const void * vy, float * dst, + const int ncols, const int nrows, + const int stride_col_y, const int stride_col_dst, + dpct::queue_ptr stream) { + GGML_ASSERT(ncols % QK_K == 0); + const int block_num_y = (nrows + GGML_SYCL_MMV_Y - 1) / GGML_SYCL_MMV_Y; + const sycl::range<3> block_nums(1, 1, block_num_y); + const sycl::range<3> block_dims(1, GGML_SYCL_MMV_Y, WARP_SIZE); + + stream->submit([&](sycl::handler & cgh) { + cgh.parallel_for( + sycl::nd_range<3>(block_nums * block_dims, block_dims), + [=](sycl::nd_item<3> item_ct1) + [[sycl::reqd_sub_group_size(WARP_SIZE)]] { + mul_mat_vec_q_ncols( + vx, vy, dst, ncols, nrows, + stride_col_y, stride_col_dst, item_ct1); + }); + }); +} + +static void mul_mat_vec_q4_K_q8_1_sycl_switch_ncols( + const void * vx, const void * vy, float * dst, + const int ncols, const int nrows, + const int ncols_dst, + const int stride_col_y, const int stride_col_dst, + dpct::queue_ptr stream) { + switch (ncols_dst) { + case 1: mul_mat_vec_q4_K_q8_1_sycl(vx, vy, dst, ncols, nrows, stream); break; + case 2: mul_mat_vec_q4_K_q8_1_sycl_ncols<2>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 3: mul_mat_vec_q4_K_q8_1_sycl_ncols<3>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 4: mul_mat_vec_q4_K_q8_1_sycl_ncols<4>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 5: mul_mat_vec_q4_K_q8_1_sycl_ncols<5>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 6: mul_mat_vec_q4_K_q8_1_sycl_ncols<6>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 7: mul_mat_vec_q4_K_q8_1_sycl_ncols<7>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 8: mul_mat_vec_q4_K_q8_1_sycl_ncols<8>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + default: GGML_ABORT("unsupported ncols_dst=%d for Q4_K multi-col MMVQ", ncols_dst); + } +} + static void reorder_mul_mat_vec_q4_k_q8_1_sycl(const void * vx, const void * vy, float * dst, const int ncols, const int nrows, dpct::queue_ptr stream) { GGML_ASSERT(ncols % QK_K == 0); @@ -834,6 +1471,44 @@ static void reorder_mul_mat_vec_q4_k_q8_1_sycl(const void * vx, const void * vy, }); } +template +static void reorder_mul_mat_vec_q4_k_q8_1_sycl_ncols( + const void * vx, const void * vy, float * dst, + const int ncols, const int nrows, + const int stride_col_y_bytes, const int stride_col_dst, + dpct::queue_ptr stream) { + GGML_ASSERT(ncols % QK_K == 0); + const int block_num_y = ceil_div(nrows, GGML_SYCL_MMV_Y); + constexpr size_t num_subgroups = 16; + GGML_ASSERT(block_num_y % num_subgroups == 0); + const sycl::range<3> global_size(1, GGML_SYCL_MMV_Y, block_num_y * WARP_SIZE); + const sycl::range<3> workgroup_size(1, GGML_SYCL_MMV_Y, num_subgroups * WARP_SIZE); + stream->submit([&](sycl::handler & cgh) { + cgh.parallel_for(sycl::nd_range<3>(global_size, workgroup_size), + [=](sycl::nd_item<3> nd_item) [[sycl::reqd_sub_group_size(WARP_SIZE)]] { + mul_mat_vec_q_reorder_ncols, ncols_dst>( + vx, vy, dst, ncols, nrows, stride_col_y_bytes, stride_col_dst, nd_item); + }); + }); +} + +static void reorder_mul_mat_vec_q4_k_q8_1_sycl_switch_ncols( + const void * vx, const void * vy, float * dst, + const int ncols, const int nrows, const int ncols_dst, + const int stride_col_y_bytes, const int stride_col_dst, + dpct::queue_ptr stream) { + switch (ncols_dst) { + case 1: reorder_mul_mat_vec_q4_k_q8_1_sycl(vx, vy, dst, ncols, nrows, stream); break; + case 2: reorder_mul_mat_vec_q4_k_q8_1_sycl_ncols<2>(vx, vy, dst, ncols, nrows, stride_col_y_bytes, stride_col_dst, stream); break; + case 3: reorder_mul_mat_vec_q4_k_q8_1_sycl_ncols<3>(vx, vy, dst, ncols, nrows, stride_col_y_bytes, stride_col_dst, stream); break; + case 4: reorder_mul_mat_vec_q4_k_q8_1_sycl_ncols<4>(vx, vy, dst, ncols, nrows, stride_col_y_bytes, stride_col_dst, stream); break; + case 5: reorder_mul_mat_vec_q4_k_q8_1_sycl_ncols<5>(vx, vy, dst, ncols, nrows, stride_col_y_bytes, stride_col_dst, stream); break; + case 6: reorder_mul_mat_vec_q4_k_q8_1_sycl_ncols<6>(vx, vy, dst, ncols, nrows, stride_col_y_bytes, stride_col_dst, stream); break; + case 7: reorder_mul_mat_vec_q4_k_q8_1_sycl_ncols<7>(vx, vy, dst, ncols, nrows, stride_col_y_bytes, stride_col_dst, stream); break; + case 8: reorder_mul_mat_vec_q4_k_q8_1_sycl_ncols<8>(vx, vy, dst, ncols, nrows, stride_col_y_bytes, stride_col_dst, stream); break; + default: GGML_ABORT("unsupported ncols_dst=%d for Q4_K reorder multi-col MMVQ", ncols_dst); + } +} static void mul_mat_vec_q5_K_q8_1_sycl(const void *vx, const void *vy, float *dst, const int ncols, @@ -859,6 +1534,51 @@ static void mul_mat_vec_q5_K_q8_1_sycl(const void *vx, const void *vy, } } +template +static void mul_mat_vec_q5_K_q8_1_sycl_ncols( + const void * vx, const void * vy, float * dst, + const int ncols, const int nrows, + const int stride_col_y, const int stride_col_dst, + dpct::queue_ptr stream) { + GGML_ASSERT(ncols % QK_K == 0); + const int block_num_y = (nrows + GGML_SYCL_MMV_Y - 1) / GGML_SYCL_MMV_Y; + const sycl::range<3> block_nums(1, 1, block_num_y); + const sycl::range<3> block_dims(1, GGML_SYCL_MMV_Y, WARP_SIZE); + + stream->submit([&](sycl::handler & cgh) { + cgh.parallel_for( + sycl::nd_range<3>(block_nums * block_dims, block_dims), + [=](sycl::nd_item<3> item_ct1) + [[sycl::reqd_sub_group_size(WARP_SIZE)]] { + mul_mat_vec_q_ncols( + vx, vy, dst, ncols, nrows, + stride_col_y, stride_col_dst, item_ct1); + }); + }); +} + +static void mul_mat_vec_q5_K_q8_1_sycl_switch_ncols( + const void * vx, const void * vy, float * dst, + const int ncols, const int nrows, + const int ncols_dst, + const int stride_col_y, const int stride_col_dst, + dpct::queue_ptr stream) { + switch (ncols_dst) { + case 1: mul_mat_vec_q5_K_q8_1_sycl(vx, vy, dst, ncols, nrows, stream); break; + case 2: mul_mat_vec_q5_K_q8_1_sycl_ncols<2>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 3: mul_mat_vec_q5_K_q8_1_sycl_ncols<3>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 4: mul_mat_vec_q5_K_q8_1_sycl_ncols<4>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 5: mul_mat_vec_q5_K_q8_1_sycl_ncols<5>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 6: mul_mat_vec_q5_K_q8_1_sycl_ncols<6>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 7: mul_mat_vec_q5_K_q8_1_sycl_ncols<7>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 8: mul_mat_vec_q5_K_q8_1_sycl_ncols<8>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + default: GGML_ABORT("unsupported ncols_dst=%d for Q5_K multi-col MMVQ", ncols_dst); + } +} + static void reorder_mul_mat_vec_q5_k_q8_1_sycl(const void * vx, const void * vy, float * dst, const int ncols, const int nrows, dpct::queue_ptr stream) { GGML_ASSERT(ncols % QK_K == 0); @@ -879,6 +1599,45 @@ static void reorder_mul_mat_vec_q5_k_q8_1_sycl(const void * vx, const void * vy, }); } +template +static void reorder_mul_mat_vec_q5_k_q8_1_sycl_ncols( + const void * vx, const void * vy, float * dst, + const int ncols, const int nrows, + const int stride_col_y_bytes, const int stride_col_dst, + dpct::queue_ptr stream) { + GGML_ASSERT(ncols % QK_K == 0); + const int block_num_y = ceil_div(nrows, GGML_SYCL_MMV_Y); + constexpr size_t num_subgroups = 16; + GGML_ASSERT(block_num_y % num_subgroups == 0); + const sycl::range<3> global_size(1, GGML_SYCL_MMV_Y, block_num_y * WARP_SIZE); + const sycl::range<3> workgroup_size(1, GGML_SYCL_MMV_Y, num_subgroups * WARP_SIZE); + stream->submit([&](sycl::handler & cgh) { + cgh.parallel_for(sycl::nd_range<3>(global_size, workgroup_size), + [=](sycl::nd_item<3> nd_item) [[sycl::reqd_sub_group_size(WARP_SIZE)]] { + mul_mat_vec_q_reorder_ncols, ncols_dst>( + vx, vy, dst, ncols, nrows, stride_col_y_bytes, stride_col_dst, nd_item); + }); + }); +} + +static void reorder_mul_mat_vec_q5_k_q8_1_sycl_switch_ncols( + const void * vx, const void * vy, float * dst, + const int ncols, const int nrows, const int ncols_dst, + const int stride_col_y_bytes, const int stride_col_dst, + dpct::queue_ptr stream) { + switch (ncols_dst) { + case 1: reorder_mul_mat_vec_q5_k_q8_1_sycl(vx, vy, dst, ncols, nrows, stream); break; + case 2: reorder_mul_mat_vec_q5_k_q8_1_sycl_ncols<2>(vx, vy, dst, ncols, nrows, stride_col_y_bytes, stride_col_dst, stream); break; + case 3: reorder_mul_mat_vec_q5_k_q8_1_sycl_ncols<3>(vx, vy, dst, ncols, nrows, stride_col_y_bytes, stride_col_dst, stream); break; + case 4: reorder_mul_mat_vec_q5_k_q8_1_sycl_ncols<4>(vx, vy, dst, ncols, nrows, stride_col_y_bytes, stride_col_dst, stream); break; + case 5: reorder_mul_mat_vec_q5_k_q8_1_sycl_ncols<5>(vx, vy, dst, ncols, nrows, stride_col_y_bytes, stride_col_dst, stream); break; + case 6: reorder_mul_mat_vec_q5_k_q8_1_sycl_ncols<6>(vx, vy, dst, ncols, nrows, stride_col_y_bytes, stride_col_dst, stream); break; + case 7: reorder_mul_mat_vec_q5_k_q8_1_sycl_ncols<7>(vx, vy, dst, ncols, nrows, stride_col_y_bytes, stride_col_dst, stream); break; + case 8: reorder_mul_mat_vec_q5_k_q8_1_sycl_ncols<8>(vx, vy, dst, ncols, nrows, stride_col_y_bytes, stride_col_dst, stream); break; + default: GGML_ABORT("unsupported ncols_dst=%d for Q5_K reorder multi-col MMVQ", ncols_dst); + } +} + static void reorder_mul_mat_vec_q6_k_q8_1_sycl(const void * vx, const void * vy, float * dst, const int ncols, const int nrows, dpct::queue_ptr stream) { GGML_ASSERT(ncols % QK_K == 0); @@ -897,6 +1656,46 @@ static void reorder_mul_mat_vec_q6_k_q8_1_sycl(const void * vx, const void * vy, }); }); } + +template +static void reorder_mul_mat_vec_q6_k_q8_1_sycl_ncols( + const void * vx, const void * vy, float * dst, + const int ncols, const int nrows, + const int stride_col_y_bytes, const int stride_col_dst, + dpct::queue_ptr stream) { + GGML_ASSERT(ncols % QK_K == 0); + const int block_num_y = ceil_div(nrows, GGML_SYCL_MMV_Y); + constexpr size_t num_subgroups = 16; + GGML_ASSERT(block_num_y % num_subgroups == 0); + const sycl::range<3> global_size(1, GGML_SYCL_MMV_Y, block_num_y * WARP_SIZE); + const sycl::range<3> workgroup_size(1, GGML_SYCL_MMV_Y, num_subgroups * WARP_SIZE); + stream->submit([&](sycl::handler & cgh) { + cgh.parallel_for(sycl::nd_range<3>(global_size, workgroup_size), + [=](sycl::nd_item<3> nd_item) [[sycl::reqd_sub_group_size(WARP_SIZE)]] { + mul_mat_vec_q_reorder_ncols, ncols_dst>( + vx, vy, dst, ncols, nrows, stride_col_y_bytes, stride_col_dst, nd_item); + }); + }); +} + +static void reorder_mul_mat_vec_q6_k_q8_1_sycl_switch_ncols( + const void * vx, const void * vy, float * dst, + const int ncols, const int nrows, const int ncols_dst, + const int stride_col_y_bytes, const int stride_col_dst, + dpct::queue_ptr stream) { + switch (ncols_dst) { + case 1: reorder_mul_mat_vec_q6_k_q8_1_sycl(vx, vy, dst, ncols, nrows, stream); break; + case 2: reorder_mul_mat_vec_q6_k_q8_1_sycl_ncols<2>(vx, vy, dst, ncols, nrows, stride_col_y_bytes, stride_col_dst, stream); break; + case 3: reorder_mul_mat_vec_q6_k_q8_1_sycl_ncols<3>(vx, vy, dst, ncols, nrows, stride_col_y_bytes, stride_col_dst, stream); break; + case 4: reorder_mul_mat_vec_q6_k_q8_1_sycl_ncols<4>(vx, vy, dst, ncols, nrows, stride_col_y_bytes, stride_col_dst, stream); break; + case 5: reorder_mul_mat_vec_q6_k_q8_1_sycl_ncols<5>(vx, vy, dst, ncols, nrows, stride_col_y_bytes, stride_col_dst, stream); break; + case 6: reorder_mul_mat_vec_q6_k_q8_1_sycl_ncols<6>(vx, vy, dst, ncols, nrows, stride_col_y_bytes, stride_col_dst, stream); break; + case 7: reorder_mul_mat_vec_q6_k_q8_1_sycl_ncols<7>(vx, vy, dst, ncols, nrows, stride_col_y_bytes, stride_col_dst, stream); break; + case 8: reorder_mul_mat_vec_q6_k_q8_1_sycl_ncols<8>(vx, vy, dst, ncols, nrows, stride_col_y_bytes, stride_col_dst, stream); break; + default: GGML_ABORT("unsupported ncols_dst=%d for Q6_K reorder multi-col MMVQ", ncols_dst); + } +} + static void mul_mat_vec_q6_K_q8_1_sycl(const void *vx, const void *vy, float *dst, const int ncols, const int nrows, @@ -921,6 +1720,51 @@ static void mul_mat_vec_q6_K_q8_1_sycl(const void *vx, const void *vy, } } +template +static void mul_mat_vec_q6_K_q8_1_sycl_ncols( + const void * vx, const void * vy, float * dst, + const int ncols, const int nrows, + const int stride_col_y, const int stride_col_dst, + dpct::queue_ptr stream) { + GGML_ASSERT(ncols % QK_K == 0); + const int block_num_y = (nrows + GGML_SYCL_MMV_Y - 1) / GGML_SYCL_MMV_Y; + const sycl::range<3> block_nums(1, 1, block_num_y); + const sycl::range<3> block_dims(1, GGML_SYCL_MMV_Y, WARP_SIZE); + + stream->submit([&](sycl::handler & cgh) { + cgh.parallel_for( + sycl::nd_range<3>(block_nums * block_dims, block_dims), + [=](sycl::nd_item<3> item_ct1) + [[sycl::reqd_sub_group_size(WARP_SIZE)]] { + mul_mat_vec_q_ncols( + vx, vy, dst, ncols, nrows, + stride_col_y, stride_col_dst, item_ct1); + }); + }); +} + +static void mul_mat_vec_q6_K_q8_1_sycl_switch_ncols( + const void * vx, const void * vy, float * dst, + const int ncols, const int nrows, + const int ncols_dst, + const int stride_col_y, const int stride_col_dst, + dpct::queue_ptr stream) { + switch (ncols_dst) { + case 1: mul_mat_vec_q6_K_q8_1_sycl(vx, vy, dst, ncols, nrows, stream); break; + case 2: mul_mat_vec_q6_K_q8_1_sycl_ncols<2>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 3: mul_mat_vec_q6_K_q8_1_sycl_ncols<3>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 4: mul_mat_vec_q6_K_q8_1_sycl_ncols<4>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 5: mul_mat_vec_q6_K_q8_1_sycl_ncols<5>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 6: mul_mat_vec_q6_K_q8_1_sycl_ncols<6>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 7: mul_mat_vec_q6_K_q8_1_sycl_ncols<7>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 8: mul_mat_vec_q6_K_q8_1_sycl_ncols<8>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + default: GGML_ABORT("unsupported ncols_dst=%d for Q6_K multi-col MMVQ", ncols_dst); + } +} + static void mul_mat_vec_iq2_xxs_q8_1_sycl(const void *vx, const void *vy, float *dst, const int ncols, @@ -1117,6 +1961,51 @@ static void mul_mat_vec_iq4_xs_q8_1_sycl(const void *vx, const void *vy, } } +template +static void mul_mat_vec_iq4_xs_q8_1_sycl_ncols( + const void * vx, const void * vy, float * dst, + const int ncols, const int nrows, + const int stride_col_y, const int stride_col_dst, + dpct::queue_ptr stream) { + GGML_ASSERT(ncols % QK_K == 0); + const int block_num_y = (nrows + GGML_SYCL_MMV_Y - 1) / GGML_SYCL_MMV_Y; + const sycl::range<3> block_nums(1, 1, block_num_y); + const sycl::range<3> block_dims(1, GGML_SYCL_MMV_Y, WARP_SIZE); + + stream->submit([&](sycl::handler & cgh) { + cgh.parallel_for( + sycl::nd_range<3>(block_nums * block_dims, block_dims), + [=](sycl::nd_item<3> item_ct1) + [[sycl::reqd_sub_group_size(WARP_SIZE)]] { + mul_mat_vec_q_ncols( + vx, vy, dst, ncols, nrows, + stride_col_y, stride_col_dst, item_ct1); + }); + }); +} + +static void mul_mat_vec_iq4_xs_q8_1_sycl_switch_ncols( + const void * vx, const void * vy, float * dst, + const int ncols, const int nrows, + const int ncols_dst, + const int stride_col_y, const int stride_col_dst, + dpct::queue_ptr stream) { + switch (ncols_dst) { + case 1: mul_mat_vec_iq4_xs_q8_1_sycl(vx, vy, dst, ncols, nrows, stream); break; + case 2: mul_mat_vec_iq4_xs_q8_1_sycl_ncols<2>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 3: mul_mat_vec_iq4_xs_q8_1_sycl_ncols<3>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 4: mul_mat_vec_iq4_xs_q8_1_sycl_ncols<4>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 5: mul_mat_vec_iq4_xs_q8_1_sycl_ncols<5>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 6: mul_mat_vec_iq4_xs_q8_1_sycl_ncols<6>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 7: mul_mat_vec_iq4_xs_q8_1_sycl_ncols<7>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + case 8: mul_mat_vec_iq4_xs_q8_1_sycl_ncols<8>(vx, vy, dst, ncols, nrows, stride_col_y, stride_col_dst, stream); break; + default: GGML_ABORT("unsupported ncols_dst=%d for IQ4_XS multi-col MMVQ", ncols_dst); + } +} + void ggml_sycl_op_mul_mat_vec_q(ggml_backend_sycl_context & ctx, const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst, const char * src0_dd_i, const float * src1_ddf_i, const char * src1_ddq_i, float * dst_dd_i, const int64_t row_low, @@ -1143,42 +2032,135 @@ void ggml_sycl_op_mul_mat_vec_q(ggml_backend_sycl_context & ctx, const ggml_tens case GGML_TYPE_Q4_0: if ((ggml_tensor_extra_gpu *) dst->src[0]->extra && ((ggml_tensor_extra_gpu *) dst->src[0]->extra)->optimized_feature.reorder) { - GGML_SYCL_DEBUG("Calling reorder_mul_mat_vec_q4_0_q8_1_sycl\n"); - reorder_mul_mat_vec_q4_0_q8_1_sycl(src0_dd_i, src1_ddq_i_bs, dst_dd_i_bs, ne00, row_diff, stream); - } else { + if (i == 0 && src1_ncols > 1 && src1_ncols <= 8) { + const int stride_col_y_bytes = src1_padded_col_size * q8_1_ts / q8_1_bs; + const int stride_col_dst = dst->ne[0]; + GGML_SYCL_DEBUG("Calling reorder_mul_mat_vec_q4_0_q8_1_sycl_switch_ncols ncols=%d\n", (int)src1_ncols); + reorder_mul_mat_vec_q4_0_q8_1_sycl_switch_ncols( + src0_dd_i, src1_ddq_i, dst_dd_i, ne00, row_diff, + src1_ncols, stride_col_y_bytes, stride_col_dst, stream); + return; + } else { + GGML_SYCL_DEBUG("Calling reorder_mul_mat_vec_q4_0_q8_1_sycl\n"); + reorder_mul_mat_vec_q4_0_q8_1_sycl(src0_dd_i, src1_ddq_i_bs, dst_dd_i_bs, ne00, row_diff, stream); + } + } else if (i == 0 && src1_ncols > 1 && src1_ncols <= 8) { + const int stride_col_y = src1_padded_col_size / QK8_1; + const int stride_col_dst = dst->ne[0]; + GGML_SYCL_DEBUG("Calling mul_mat_vec_q4_0_q8_1_sycl_switch_ncols ncols=%d\n", (int)src1_ncols); + mul_mat_vec_q4_0_q8_1_sycl_switch_ncols( + src0_dd_i, src1_ddq_i, dst_dd_i, ne00, row_diff, + src1_ncols, stride_col_y, stride_col_dst, stream); + return; + } else if (i == 0 || src1_ncols == 1) { GGML_SYCL_DEBUG("Calling mul_mat_vec_q4_0_q8_1_sycl\n"); mul_mat_vec_q4_0_q8_1_sycl(src0_dd_i, src1_ddq_i_bs, dst_dd_i_bs, ne00, row_diff, stream); } break; case GGML_TYPE_Q4_1: - mul_mat_vec_q4_1_q8_1_sycl(src0_dd_i, src1_ddq_i_bs, dst_dd_i_bs, ne00, row_diff, stream); + if (i == 0 && src1_ncols > 1 && src1_ncols <= 8) { + const int stride_col_y = src1_padded_col_size / QK8_1; + const int stride_col_dst = dst->ne[0]; + GGML_SYCL_DEBUG("Calling mul_mat_vec_q4_1_q8_1_sycl_switch_ncols ncols=%d\n", (int)src1_ncols); + mul_mat_vec_q4_1_q8_1_sycl_switch_ncols( + src0_dd_i, src1_ddq_i, dst_dd_i, ne00, row_diff, + src1_ncols, stride_col_y, stride_col_dst, stream); + return; + } else if (i == 0 || src1_ncols == 1) { + mul_mat_vec_q4_1_q8_1_sycl(src0_dd_i, src1_ddq_i_bs, dst_dd_i_bs, ne00, row_diff, stream); + } break; case GGML_TYPE_Q5_0: - mul_mat_vec_q5_0_q8_1_sycl(src0_dd_i, src1_ddq_i_bs, dst_dd_i_bs, ne00, row_diff, stream); + if (i == 0 && src1_ncols > 1 && src1_ncols <= 8) { + const int stride_col_y = src1_padded_col_size / QK8_1; + const int stride_col_dst = dst->ne[0]; + GGML_SYCL_DEBUG("Calling mul_mat_vec_q5_0_q8_1_sycl_switch_ncols ncols=%d\n", (int)src1_ncols); + mul_mat_vec_q5_0_q8_1_sycl_switch_ncols( + src0_dd_i, src1_ddq_i, dst_dd_i, ne00, row_diff, + src1_ncols, stride_col_y, stride_col_dst, stream); + return; + } else if (i == 0 || src1_ncols == 1) { + mul_mat_vec_q5_0_q8_1_sycl(src0_dd_i, src1_ddq_i_bs, dst_dd_i_bs, ne00, row_diff, stream); + } break; case GGML_TYPE_Q5_1: - mul_mat_vec_q5_1_q8_1_sycl(src0_dd_i, src1_ddq_i_bs, dst_dd_i_bs, ne00, row_diff, stream); + if (i == 0 && src1_ncols > 1 && src1_ncols <= 8) { + const int stride_col_y = src1_padded_col_size / QK8_1; + const int stride_col_dst = dst->ne[0]; + GGML_SYCL_DEBUG("Calling mul_mat_vec_q5_1_q8_1_sycl_switch_ncols ncols=%d\n", (int)src1_ncols); + mul_mat_vec_q5_1_q8_1_sycl_switch_ncols( + src0_dd_i, src1_ddq_i, dst_dd_i, ne00, row_diff, + src1_ncols, stride_col_y, stride_col_dst, stream); + return; + } else if (i == 0 || src1_ncols == 1) { + mul_mat_vec_q5_1_q8_1_sycl(src0_dd_i, src1_ddq_i_bs, dst_dd_i_bs, ne00, row_diff, stream); + } break; case GGML_TYPE_Q8_0: if ((ggml_tensor_extra_gpu *) dst->src[0]->extra && ((ggml_tensor_extra_gpu *) dst->src[0]->extra)->optimized_feature.reorder) { - GGML_SYCL_DEBUG("Calling reorder_mul_mat_vec_q8_0_q8_1_sycl\n"); - reorder_mul_mat_vec_q8_0_q8_1_sycl(src0_dd_i, src1_ddq_i_bs, dst_dd_i_bs, ne00, row_diff, stream); - } else { + if (i == 0 && src1_ncols > 1 && src1_ncols <= 8) { + const int stride_col_y_bytes = src1_padded_col_size * q8_1_ts / q8_1_bs; + const int stride_col_dst = dst->ne[0]; + GGML_SYCL_DEBUG("Calling reorder_mul_mat_vec_q8_0_q8_1_sycl_switch_ncols ncols=%d\n", (int)src1_ncols); + reorder_mul_mat_vec_q8_0_q8_1_sycl_switch_ncols( + src0_dd_i, src1_ddq_i, dst_dd_i, ne00, row_diff, + src1_ncols, stride_col_y_bytes, stride_col_dst, stream); + return; + } else { + GGML_SYCL_DEBUG("Calling reorder_mul_mat_vec_q8_0_q8_1_sycl\n"); + reorder_mul_mat_vec_q8_0_q8_1_sycl(src0_dd_i, src1_ddq_i_bs, dst_dd_i_bs, ne00, row_diff, stream); + } + } else if (i == 0 && src1_ncols > 1 && src1_ncols <= 8) { + const int stride_col_y = src1_padded_col_size / QK8_1; + const int stride_col_dst = dst->ne[0]; + GGML_SYCL_DEBUG("Calling mul_mat_vec_q8_0_q8_1_sycl_switch_ncols ncols=%d\n", (int)src1_ncols); + mul_mat_vec_q8_0_q8_1_sycl_switch_ncols( + src0_dd_i, src1_ddq_i, dst_dd_i, ne00, row_diff, + src1_ncols, stride_col_y, stride_col_dst, stream); + return; + } else if (i == 0 || src1_ncols == 1) { GGML_SYCL_DEBUG("Calling mul_mat_vec_q8_0_q8_1_sycl\n"); mul_mat_vec_q8_0_q8_1_sycl(src0_dd_i, src1_ddq_i_bs, dst_dd_i_bs, ne00, row_diff, stream); } break; case GGML_TYPE_Q2_K: - mul_mat_vec_q2_K_q8_1_sycl(src0_dd_i, src1_ddq_i_bs, dst_dd_i_bs, ne00, row_diff, stream); + if (i == 0 && src1_ncols > 1 && src1_ncols <= 8) { + const int stride_col_y = src1_padded_col_size / QK8_1; + const int stride_col_dst = dst->ne[0]; + GGML_SYCL_DEBUG("Calling mul_mat_vec_q2_K_q8_1_sycl_switch_ncols ncols=%d\n", (int)src1_ncols); + mul_mat_vec_q2_K_q8_1_sycl_switch_ncols( + src0_dd_i, src1_ddq_i, dst_dd_i, ne00, row_diff, + src1_ncols, stride_col_y, stride_col_dst, stream); + return; + } else if (i == 0 || src1_ncols == 1) { + mul_mat_vec_q2_K_q8_1_sycl(src0_dd_i, src1_ddq_i_bs, dst_dd_i_bs, ne00, row_diff, stream); + } break; case GGML_TYPE_Q3_K: if ((ggml_tensor_extra_gpu *) dst->src[0]->extra && ((ggml_tensor_extra_gpu *) dst->src[0]->extra)->optimized_feature.reorder) { - GGML_SYCL_DEBUG("Calling reorder_mul_mat_vec_q3_k_q8_1_sycl\n"); - reorder_mul_mat_vec_q3_k_q8_1_sycl(src0_dd_i, src1_ddq_i_bs, dst_dd_i_bs, ne00, row_diff, - stream); - } else { + if (i == 0 && src1_ncols > 1 && src1_ncols <= 8) { + const int stride_col_y_bytes = src1_padded_col_size * q8_1_ts / q8_1_bs; + const int stride_col_dst = dst->ne[0]; + GGML_SYCL_DEBUG("Calling reorder_mul_mat_vec_q3_k_q8_1_sycl_switch_ncols ncols=%d\n", (int)src1_ncols); + reorder_mul_mat_vec_q3_k_q8_1_sycl_switch_ncols( + src0_dd_i, src1_ddq_i, dst_dd_i, ne00, row_diff, + src1_ncols, stride_col_y_bytes, stride_col_dst, stream); + return; + } else { + GGML_SYCL_DEBUG("Calling reorder_mul_mat_vec_q3_k_q8_1_sycl\n"); + reorder_mul_mat_vec_q3_k_q8_1_sycl(src0_dd_i, src1_ddq_i_bs, dst_dd_i_bs, ne00, row_diff, stream); + } + } else if (i == 0 && src1_ncols > 1 && src1_ncols <= 8) { + const int stride_col_y = src1_padded_col_size / QK8_1; + const int stride_col_dst = dst->ne[0]; + GGML_SYCL_DEBUG("Calling mul_mat_vec_q3_K_q8_1_sycl_switch_ncols ncols=%d\n", (int)src1_ncols); + mul_mat_vec_q3_K_q8_1_sycl_switch_ncols( + src0_dd_i, src1_ddq_i, dst_dd_i, ne00, row_diff, + src1_ncols, stride_col_y, stride_col_dst, stream); + return; + } else if (i == 0 || src1_ncols == 1) { GGML_SYCL_DEBUG("Calling mul_mat_vec_q3_K_q8_1_sycl\n"); mul_mat_vec_q3_K_q8_1_sycl(src0_dd_i, src1_ddq_i_bs, dst_dd_i_bs, ne00, row_diff, stream); } @@ -1186,9 +2168,27 @@ void ggml_sycl_op_mul_mat_vec_q(ggml_backend_sycl_context & ctx, const ggml_tens case GGML_TYPE_Q4_K: if ((ggml_tensor_extra_gpu *) dst->src[0]->extra && ((ggml_tensor_extra_gpu *) dst->src[0]->extra)->optimized_feature.reorder) { - GGML_SYCL_DEBUG("Calling reorder_mul_mat_vec_q4_k_q8_1_sycl\n"); - reorder_mul_mat_vec_q4_k_q8_1_sycl(src0_dd_i, src1_ddq_i_bs, dst_dd_i_bs, ne00, row_diff, stream); - } else { + if (i == 0 && src1_ncols > 1 && src1_ncols <= 8) { + const int stride_col_y_bytes = src1_padded_col_size * q8_1_ts / q8_1_bs; + const int stride_col_dst = dst->ne[0]; + GGML_SYCL_DEBUG("Calling reorder_mul_mat_vec_q4_k_q8_1_sycl_switch_ncols ncols=%d\n", (int)src1_ncols); + reorder_mul_mat_vec_q4_k_q8_1_sycl_switch_ncols( + src0_dd_i, src1_ddq_i, dst_dd_i, ne00, row_diff, + src1_ncols, stride_col_y_bytes, stride_col_dst, stream); + return; + } else { + GGML_SYCL_DEBUG("Calling reorder_mul_mat_vec_q4_k_q8_1_sycl\n"); + reorder_mul_mat_vec_q4_k_q8_1_sycl(src0_dd_i, src1_ddq_i_bs, dst_dd_i_bs, ne00, row_diff, stream); + } + } else if (i == 0 && src1_ncols > 1 && src1_ncols <= 8) { + const int stride_col_y = src1_padded_col_size / QK8_1; + const int stride_col_dst = dst->ne[0]; + GGML_SYCL_DEBUG("Calling mul_mat_vec_q4_K_q8_1_sycl_switch_ncols ncols=%d\n", (int)src1_ncols); + mul_mat_vec_q4_K_q8_1_sycl_switch_ncols( + src0_dd_i, src1_ddq_i, dst_dd_i, ne00, row_diff, + src1_ncols, stride_col_y, stride_col_dst, stream); + return; + } else if (i == 0 || src1_ncols == 1) { GGML_SYCL_DEBUG("Calling mul_mat_vec_q4_K_q8_1_sycl\n"); mul_mat_vec_q4_K_q8_1_sycl(src0_dd_i, src1_ddq_i_bs, dst_dd_i_bs, ne00, row_diff, stream); } @@ -1196,9 +2196,27 @@ void ggml_sycl_op_mul_mat_vec_q(ggml_backend_sycl_context & ctx, const ggml_tens case GGML_TYPE_Q5_K: if ((ggml_tensor_extra_gpu *) dst->src[0]->extra && ((ggml_tensor_extra_gpu *) dst->src[0]->extra)->optimized_feature.reorder) { - GGML_SYCL_DEBUG("Calling reorder_mul_mat_vec_q5_k_q8_1_sycl\n"); - reorder_mul_mat_vec_q5_k_q8_1_sycl(src0_dd_i, src1_ddq_i_bs, dst_dd_i_bs, ne00, row_diff, stream); - } else { + if (i == 0 && src1_ncols > 1 && src1_ncols <= 8) { + const int stride_col_y_bytes = src1_padded_col_size * q8_1_ts / q8_1_bs; + const int stride_col_dst = dst->ne[0]; + GGML_SYCL_DEBUG("Calling reorder_mul_mat_vec_q5_k_q8_1_sycl_switch_ncols ncols=%d\n", (int)src1_ncols); + reorder_mul_mat_vec_q5_k_q8_1_sycl_switch_ncols( + src0_dd_i, src1_ddq_i, dst_dd_i, ne00, row_diff, + src1_ncols, stride_col_y_bytes, stride_col_dst, stream); + return; + } else { + GGML_SYCL_DEBUG("Calling reorder_mul_mat_vec_q5_k_q8_1_sycl\n"); + reorder_mul_mat_vec_q5_k_q8_1_sycl(src0_dd_i, src1_ddq_i_bs, dst_dd_i_bs, ne00, row_diff, stream); + } + } else if (i == 0 && src1_ncols > 1 && src1_ncols <= 8) { + const int stride_col_y = src1_padded_col_size / QK8_1; + const int stride_col_dst = dst->ne[0]; + GGML_SYCL_DEBUG("Calling mul_mat_vec_q5_K_q8_1_sycl_switch_ncols ncols=%d\n", (int)src1_ncols); + mul_mat_vec_q5_K_q8_1_sycl_switch_ncols( + src0_dd_i, src1_ddq_i, dst_dd_i, ne00, row_diff, + src1_ncols, stride_col_y, stride_col_dst, stream); + return; + } else if (i == 0 || src1_ncols == 1) { GGML_SYCL_DEBUG("Calling mul_mat_vec_q5_K_q8_1_sycl\n"); mul_mat_vec_q5_K_q8_1_sycl(src0_dd_i, src1_ddq_i_bs, dst_dd_i_bs, ne00, row_diff, stream); } @@ -1206,9 +2224,27 @@ void ggml_sycl_op_mul_mat_vec_q(ggml_backend_sycl_context & ctx, const ggml_tens case GGML_TYPE_Q6_K: if ((ggml_tensor_extra_gpu *) dst->src[0]->extra && ((ggml_tensor_extra_gpu *) dst->src[0]->extra)->optimized_feature.reorder) { - GGML_SYCL_DEBUG("Calling reorder_mul_mat_vec_q6_k_q8_1_sycl\n"); - reorder_mul_mat_vec_q6_k_q8_1_sycl(src0_dd_i, src1_ddq_i_bs, dst_dd_i_bs, ne00, row_diff, stream); - } else { + if (i == 0 && src1_ncols > 1 && src1_ncols <= 8) { + const int stride_col_y_bytes = src1_padded_col_size * q8_1_ts / q8_1_bs; + const int stride_col_dst = dst->ne[0]; + GGML_SYCL_DEBUG("Calling reorder_mul_mat_vec_q6_k_q8_1_sycl_switch_ncols ncols=%d\n", (int)src1_ncols); + reorder_mul_mat_vec_q6_k_q8_1_sycl_switch_ncols( + src0_dd_i, src1_ddq_i, dst_dd_i, ne00, row_diff, + src1_ncols, stride_col_y_bytes, stride_col_dst, stream); + return; + } else { + GGML_SYCL_DEBUG("Calling reorder_mul_mat_vec_q6_k_q8_1_sycl\n"); + reorder_mul_mat_vec_q6_k_q8_1_sycl(src0_dd_i, src1_ddq_i_bs, dst_dd_i_bs, ne00, row_diff, stream); + } + } else if (i == 0 && src1_ncols > 1 && src1_ncols <= 8) { + const int stride_col_y = src1_padded_col_size / QK8_1; + const int stride_col_dst = dst->ne[0]; + GGML_SYCL_DEBUG("Calling mul_mat_vec_q6_K_q8_1_sycl_switch_ncols ncols=%d\n", (int)src1_ncols); + mul_mat_vec_q6_K_q8_1_sycl_switch_ncols( + src0_dd_i, src1_ddq_i, dst_dd_i, ne00, row_diff, + src1_ncols, stride_col_y, stride_col_dst, stream); + return; + } else if (i == 0 || src1_ncols == 1) { GGML_SYCL_DEBUG("Calling mul_mat_vec_q6_k_q8_1_sycl\n"); mul_mat_vec_q6_K_q8_1_sycl(src0_dd_i, src1_ddq_i_bs, dst_dd_i_bs, ne00, row_diff, stream); } @@ -1238,13 +2274,43 @@ void ggml_sycl_op_mul_mat_vec_q(ggml_backend_sycl_context & ctx, const ggml_tens mul_mat_vec_iq4_nl_q8_1_sycl(src0_dd_i, src1_ddq_i_bs, dst_dd_i_bs, ne00, row_diff, stream); break; case GGML_TYPE_IQ4_XS: - mul_mat_vec_iq4_xs_q8_1_sycl(src0_dd_i, src1_ddq_i_bs, dst_dd_i_bs, ne00, row_diff, stream); + if (i == 0 && src1_ncols > 1 && src1_ncols <= 8) { + const int stride_col_y = src1_padded_col_size / QK8_1; + const int stride_col_dst = dst->ne[0]; + GGML_SYCL_DEBUG("Calling mul_mat_vec_iq4_xs_q8_1_sycl_switch_ncols ncols=%d\n", (int)src1_ncols); + mul_mat_vec_iq4_xs_q8_1_sycl_switch_ncols( + src0_dd_i, src1_ddq_i, dst_dd_i, ne00, row_diff, + src1_ncols, stride_col_y, stride_col_dst, stream); + return; + } else if (i == 0 || src1_ncols == 1) { + mul_mat_vec_iq4_xs_q8_1_sycl(src0_dd_i, src1_ddq_i_bs, dst_dd_i_bs, ne00, row_diff, stream); + } break; case GGML_TYPE_MXFP4: - mul_mat_vec_mxfp4_q8_1_sycl(src0_dd_i, src1_ddq_i_bs, dst_dd_i_bs, ne00, row_diff, stream); + if (i == 0 && src1_ncols > 1 && src1_ncols <= 8) { + const int stride_col_y = src1_padded_col_size / QK8_1; + const int stride_col_dst = dst->ne[0]; + GGML_SYCL_DEBUG("Calling mul_mat_vec_mxfp4_q8_1_sycl_switch_ncols ncols=%d\n", (int)src1_ncols); + mul_mat_vec_mxfp4_q8_1_sycl_switch_ncols( + src0_dd_i, src1_ddq_i, dst_dd_i, ne00, row_diff, + src1_ncols, stride_col_y, stride_col_dst, stream); + return; + } else if (i == 0 || src1_ncols == 1) { + mul_mat_vec_mxfp4_q8_1_sycl(src0_dd_i, src1_ddq_i_bs, dst_dd_i_bs, ne00, row_diff, stream); + } break; case GGML_TYPE_NVFP4: - mul_mat_vec_nvfp4_q8_1_sycl(src0_dd_i, src1_ddq_i_bs, dst_dd_i_bs, ne00, row_diff, stream); + if (i == 0 && src1_ncols > 1 && src1_ncols <= 8) { + const int stride_col_y = src1_padded_col_size / QK8_1; + const int stride_col_dst = dst->ne[0]; + GGML_SYCL_DEBUG("Calling mul_mat_vec_nvfp4_q8_1_sycl_switch_ncols ncols=%d\n", (int)src1_ncols); + mul_mat_vec_nvfp4_q8_1_sycl_switch_ncols( + src0_dd_i, src1_ddq_i, dst_dd_i, ne00, row_diff, + src1_ncols, stride_col_y, stride_col_dst, stream); + return; + } else if (i == 0 || src1_ncols == 1) { + mul_mat_vec_nvfp4_q8_1_sycl(src0_dd_i, src1_ddq_i_bs, dst_dd_i_bs, ne00, row_diff, stream); + } break; default: GGML_ABORT("fatal error: unsupport data type=%s\n", ggml_type_name(src0->type)); diff --git a/gguf-py/gguf/constants.py b/gguf-py/gguf/constants.py index ce556ec9b655..26ab31c19f11 100644 --- a/gguf-py/gguf/constants.py +++ b/gguf-py/gguf/constants.py @@ -434,6 +434,7 @@ class MODEL_ARCH(IntEnum): GEMMA3 = auto() GEMMA3N = auto() GEMMA4 = auto() + GEMMA4_ASSISTANT = auto() GEMMA_EMBEDDING = auto() STARCODER2 = auto() RWKV6 = auto() @@ -866,6 +867,8 @@ class MODEL_TENSOR(IntEnum): A_PER_DIM_K_SCALE = auto() # gemma4 A_PER_DIM_SCALE = auto() # gemma4 # nextn/mtp + NEXTN_PRE_PROJ = auto() + NEXTN_POST_PROJ = auto() NEXTN_EH_PROJ = auto() NEXTN_EMBED_TOKENS = auto() NEXTN_ENORM = auto() @@ -955,6 +958,7 @@ class MODEL_TENSOR(IntEnum): MODEL_ARCH.GEMMA3: "gemma3", MODEL_ARCH.GEMMA3N: "gemma3n", MODEL_ARCH.GEMMA4: "gemma4", + MODEL_ARCH.GEMMA4_ASSISTANT: "gemma4-assistant", MODEL_ARCH.GEMMA_EMBEDDING: "gemma-embedding", MODEL_ARCH.STARCODER2: "starcoder2", MODEL_ARCH.RWKV6: "rwkv6", @@ -1417,6 +1421,8 @@ class MODEL_TENSOR(IntEnum): MODEL_TENSOR.A_QF_FFN_DOWN: "a.proj_blk.{bid}.ffn_down", MODEL_TENSOR.A_QF_FFN_NORM: "a.proj_blk.{bid}.ffn_norm", # NextN/MTP + MODEL_TENSOR.NEXTN_PRE_PROJ: "nextn.pre_projection", + MODEL_TENSOR.NEXTN_POST_PROJ: "nextn.post_projection", MODEL_TENSOR.NEXTN_EH_PROJ: "blk.{bid}.nextn.eh_proj", MODEL_TENSOR.NEXTN_EMBED_TOKENS: "blk.{bid}.nextn.embed_tokens", MODEL_TENSOR.NEXTN_ENORM: "blk.{bid}.nextn.enorm", @@ -2500,6 +2506,24 @@ class MODEL_TENSOR(IntEnum): MODEL_TENSOR.PER_LAYER_PROJ_NORM, MODEL_TENSOR.PER_LAYER_POST_NORM, ], + MODEL_ARCH.GEMMA4_ASSISTANT: [ + MODEL_TENSOR.ROPE_FREQS, + MODEL_TENSOR.TOKEN_EMBD, + MODEL_TENSOR.OUTPUT_NORM, + MODEL_TENSOR.NEXTN_PRE_PROJ, + MODEL_TENSOR.NEXTN_POST_PROJ, + MODEL_TENSOR.ATTN_Q, + MODEL_TENSOR.ATTN_Q_NORM, + MODEL_TENSOR.ATTN_OUT, + MODEL_TENSOR.FFN_GATE, + MODEL_TENSOR.FFN_DOWN, + MODEL_TENSOR.FFN_UP, + MODEL_TENSOR.ATTN_NORM, + MODEL_TENSOR.ATTN_POST_NORM, + MODEL_TENSOR.FFN_PRE_NORM, + MODEL_TENSOR.FFN_POST_NORM, + MODEL_TENSOR.LAYER_OUT_SCALE, + ], MODEL_ARCH.GEMMA_EMBEDDING: [ MODEL_TENSOR.TOKEN_EMBD, MODEL_TENSOR.OUTPUT, diff --git a/gguf-py/gguf/tensor_mapping.py b/gguf-py/gguf/tensor_mapping.py index 82f26e7b303d..909544ed1dea 100644 --- a/gguf-py/gguf/tensor_mapping.py +++ b/gguf-py/gguf/tensor_mapping.py @@ -2279,6 +2279,14 @@ class TensorNameMap: ), # NextN/MTP tensors + MODEL_TENSOR.NEXTN_PRE_PROJ: ( + "pre_projection", + ), + + MODEL_TENSOR.NEXTN_POST_PROJ: ( + "post_projection", + ), + MODEL_TENSOR.NEXTN_EH_PROJ: ( "model.layers.{bid}.eh_proj", ), diff --git a/src/llama-adapter.cpp b/src/llama-adapter.cpp index 4a1aaa955a87..3e0fe66afff7 100644 --- a/src/llama-adapter.cpp +++ b/src/llama-adapter.cpp @@ -41,7 +41,7 @@ bool llama_adapter_cvec::init(const llama_model & model) { auto it = ctx_map.find(buft); if (it == ctx_map.end()) { ggml_init_params params = { - /*.mem_size =*/ hparams.n_layer*ggml_tensor_overhead(), + /*.mem_size =*/ hparams.n_layer()*ggml_tensor_overhead(), /*.mem_buffer =*/ NULL, /*.no_alloc =*/ true, }; @@ -61,9 +61,9 @@ bool llama_adapter_cvec::init(const llama_model & model) { }; // make tensors - tensors.reserve(hparams.n_layer); + tensors.reserve(hparams.n_layer()); tensors.push_back(nullptr); // there's never a tensor for layer 0 - for (size_t il = 1; il < hparams.n_layer; il++) { + for (size_t il = 1; il < hparams.n_layer(); il++) { ggml_backend_buffer_type_t buft = model.select_buft(il); ggml_context * ctx = ctx_for_buft(buft); if (!ctx) { @@ -121,7 +121,7 @@ bool llama_adapter_cvec::apply( layer_start = il_start; layer_end = il_end; - for (size_t il = 1; il < hparams.n_layer; il++) { + for (size_t il = 1; il < hparams.n_layer(); il++) { assert(tensors[il] != nullptr); const size_t off = n_embd * (il - 1); // buffer doesn't have data for layer 0, since it's never present diff --git a/src/llama-arch.cpp b/src/llama-arch.cpp index fea898deaf2c..eaf0494aabc0 100644 --- a/src/llama-arch.cpp +++ b/src/llama-arch.cpp @@ -57,6 +57,7 @@ static const std::map LLM_ARCH_NAMES = { { LLM_ARCH_GEMMA3, "gemma3" }, { LLM_ARCH_GEMMA3N, "gemma3n" }, { LLM_ARCH_GEMMA4, "gemma4" }, + { LLM_ARCH_GEMMA4_ASSISTANT, "gemma4-assistant" }, { LLM_ARCH_GEMMA_EMBEDDING, "gemma-embedding" }, { LLM_ARCH_STARCODER2, "starcoder2" }, { LLM_ARCH_MAMBA, "mamba" }, @@ -452,6 +453,8 @@ static const std::map LLM_TENSOR_NAMES = { { LLM_TENSOR_FFN_NORM_EXPS, "blk.%d.ffn_norm_exps" }, { LLM_TENSOR_ATTN_K_B, "blk.%d.attn_k_b" }, { LLM_TENSOR_ATTN_V_B, "blk.%d.attn_v_b" }, + { LLM_TENSOR_NEXTN_PRE_PROJ, "nextn.pre_projection" }, + { LLM_TENSOR_NEXTN_POST_PROJ, "nextn.post_projection" }, { LLM_TENSOR_NEXTN_EH_PROJ, "blk.%d.nextn.eh_proj" }, { LLM_TENSOR_NEXTN_EMBED_TOKENS, "blk.%d.nextn.embed_tokens" }, { LLM_TENSOR_NEXTN_ENORM, "blk.%d.nextn.enorm" }, @@ -764,6 +767,8 @@ static const std::map LLM_TENSOR_INFOS = { {LLM_TENSOR_INDEXER_PROJ, {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}}, {LLM_TENSOR_INDEXER_ATTN_K, {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}}, {LLM_TENSOR_INDEXER_ATTN_Q_B, {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}}, + {LLM_TENSOR_NEXTN_PRE_PROJ, {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}}, + {LLM_TENSOR_NEXTN_POST_PROJ, {LLM_TENSOR_LAYER_OUTPUT, GGML_OP_MUL_MAT}}, // NextN/MTP tensors are stored per-block (blk.%d.nextn.*) even though only the // last nextn_predict_layers blocks carry them. Classify as LAYER_REPEATING so // the model loader doesn't fault on the block index. diff --git a/src/llama-arch.h b/src/llama-arch.h index f364f6b0bae1..1e71c19be471 100644 --- a/src/llama-arch.h +++ b/src/llama-arch.h @@ -61,6 +61,7 @@ enum llm_arch { LLM_ARCH_GEMMA3, LLM_ARCH_GEMMA3N, LLM_ARCH_GEMMA4, + LLM_ARCH_GEMMA4_ASSISTANT, LLM_ARCH_GEMMA_EMBEDDING, LLM_ARCH_STARCODER2, LLM_ARCH_MAMBA, @@ -556,6 +557,8 @@ enum llm_tensor { LLM_TENSOR_INDEXER_PROJ, LLM_TENSOR_INDEXER_ATTN_K, LLM_TENSOR_INDEXER_ATTN_Q_B, + LLM_TENSOR_NEXTN_PRE_PROJ, // TODO: rename to PROJ_PRE + LLM_TENSOR_NEXTN_POST_PROJ, // TODO: rename to PROJ_POST LLM_TENSOR_NEXTN_EH_PROJ, LLM_TENSOR_NEXTN_EMBED_TOKENS, LLM_TENSOR_NEXTN_ENORM, diff --git a/src/llama-context.cpp b/src/llama-context.cpp index f59381a4d757..5daa80cfe89d 100644 --- a/src/llama-context.cpp +++ b/src/llama-context.cpp @@ -30,6 +30,70 @@ static llm_graph_type ctx_type_to_graph_type(llama_context_type ctx_type) { throw std::runtime_error("Unsupported ctx type"); } +static uint32_t ctx_type_to_embd_inp(const llama_hparams & hparams, llama_context_type ctx_type) { + switch (ctx_type) { + case LLAMA_CONTEXT_TYPE_DEFAULT: return hparams.n_embd_inp(); + case LLAMA_CONTEXT_TYPE_MTP : return hparams.n_embd_out(); + } + throw std::runtime_error("Unsupported ctx type"); +} + +namespace { +struct src_mctx_reset_on_exit { + llama_memory_context_ptr * slot; + ~src_mctx_reset_on_exit() { if (slot) slot->reset(); } +}; + +static void llama_assert_gemma4_mtp_source_placement( + const llama_context * ctx, + const llama_context * src) { + if (!ctx || !src) { + return; + } + + const auto & model_dft = ctx->get_model(); + const auto & model_tgt = src->get_model(); + + if (model_dft.arch != LLM_ARCH_GEMMA4_ASSISTANT || model_tgt.arch != LLM_ARCH_GEMMA4) { + return; + } + + if (model_tgt.split_mode() == LLAMA_SPLIT_MODE_TENSOR) { + return; + } + + const auto & hparams_dft = model_dft.hparams; + const auto & hparams_tgt = model_tgt.hparams; + + const int32_t il_tgt_full = (int32_t) hparams_tgt.n_layer() - 1; + const int32_t il_tgt_swa = (int32_t) hparams_tgt.n_layer() - 2; + + ggml_backend_dev_t dev_cpu = ggml_backend_dev_by_type(GGML_BACKEND_DEVICE_TYPE_CPU); + if (!dev_cpu) { + throw std::runtime_error("Gemma 4 assistant MTP placement check failed: no CPU backend found"); + } + + const bool kv_offload = src->get_cparams().offload_kqv; + + for (uint32_t il_dft = 0; il_dft < hparams_dft.n_layer(); ++il_dft) { + const int32_t il_tgt = hparams_dft.is_swa(il_dft) ? il_tgt_swa : il_tgt_full; + + ggml_backend_dev_t dev_dft = model_dft.dev_layer(il_dft); + ggml_backend_dev_t dev_kv = kv_offload ? model_tgt.dev_layer(il_tgt) : dev_cpu; + + if (dev_dft != dev_kv) { + throw std::runtime_error(format( + "Gemma 4 assistant MTP placement mismatch: draft layer %d is on %s, " + "but shared target KV layer %d is on %s", + (int) il_dft, + ggml_backend_dev_name(dev_dft), + (int) il_tgt, + ggml_backend_dev_name(dev_kv))); + } + } +} +} + llama_context::llama_context( const llama_model & model, llama_context_params params) : @@ -341,7 +405,7 @@ llama_context::llama_context( // enabling pipeline parallelism in the scheduler increases memory usage, so it is only done when necessary bool pipeline_parallel = model.n_devices() > 1 && - model.n_gpu_layers() > model.hparams.n_layer && + model.n_gpu_layers() > model.hparams.n_layer() && model.split_mode() == LLAMA_SPLIT_MODE_LAYER && cparams.offload_kqv && !model.has_tensor_overrides(); @@ -372,7 +436,11 @@ llama_context::llama_context( LLAMA_LOG_INFO("%s: pipeline parallelism enabled\n", __func__); } - sched_reserve(); + // MTP draft contexts can't reserve until the source context is wired + // via llama_set_mtp_source — defer to the first decode. + if (cparams.ctx_type != LLAMA_CONTEXT_TYPE_MTP) { + sched_reserve(); + } if (!cparams.flash_attn) { if (ggml_is_quantized(params.type_v)) { @@ -446,6 +514,23 @@ void llama_context::sched_reserve() { } } + // When called from decode(), src_mctx_for_decode is already populated and + // we must not drop it on exit (process_ubatch still needs it). Snapshot + // only when sched_reserve runs standalone (e.g. lazy first-decode reserve + // when set_mtp_source flipped sched_need_reserve). + const bool owns_src_snapshot = src_ctx && !src_mctx_for_decode; + if (owns_src_snapshot) { + auto * src_memory = src_ctx->get_memory(); + if (!src_memory) { + throw std::runtime_error("MTP source context has no memory module"); + } + src_mctx_for_decode = src_memory->init_full(); + if (!src_mctx_for_decode) { + throw std::runtime_error("failed to initialize MTP source memory snapshot"); + } + } + src_mctx_reset_on_exit reserve_src_drop{owns_src_snapshot ? &src_mctx_for_decode : nullptr}; + // avoid reserving graphs with zero outputs - assume one output per sequence const int n_outputs = n_seqs; @@ -904,7 +989,7 @@ float * llama_context::get_embeddings_nextn_ith(int32_t i) { throw std::runtime_error("no nextn embeddings"); } - const uint32_t n_embd = model.hparams.n_embd; + const uint32_t n_embd = model.hparams.n_embd_out(); if (!cparams.embeddings_nextn_masked) { // unmasked: nextn rows are stored densely, indexed by raw token position. @@ -1113,6 +1198,18 @@ void llama_context::set_embeddings_nextn(bool value, bool masked) { cparams.embeddings_nextn_masked = masked; } +void llama_context::set_mtp_source(llama_context * src) { + if (src_ctx == src) { + return; + } + llama_assert_gemma4_mtp_source_placement(this, src); + src_ctx = src; + src_mctx_for_decode.reset(); + // worst-case compute buffers were reserved without knowing about the source + // memory; force a re-reserve so the next decode sees src views + sched_need_reserve = true; +} + void llama_context::set_causal_attn(bool value) { LLAMA_LOG_DEBUG("%s: value = %d\n", __func__, value); @@ -1338,7 +1435,7 @@ int llama_context::encode(const llama_batch & batch_inp) { const auto & hparams = model.hparams; - const int64_t n_embd = hparams.n_embd_inp(); + const int64_t n_embd = ctx_type_to_embd_inp(hparams, cparams.ctx_type); const int64_t n_vocab = model.vocab.n_tokens(); // note: during encode, we always pass the full sequence starting from pos = 0 @@ -1473,7 +1570,7 @@ int llama_context::encode(const llama_batch & batch_inp) { ggml_backend_t backend_h = ggml_backend_sched_get_tensor_backend(sched.get(), t_h_nextn); GGML_ASSERT(backend_h != nullptr); - const uint32_t n_embd = hparams.n_embd; + const uint32_t n_embd = hparams.n_embd_out(); GGML_ASSERT(n_tokens*n_embd <= (int64_t) embd_nextn.size); ggml_backend_tensor_get_async(backend_h, t_h_nextn, embd_nextn.data, 0, n_tokens*n_embd*sizeof(float)); } @@ -1648,7 +1745,7 @@ int llama_context::decode(const llama_batch & batch_inp) { const auto & hparams = model.hparams; const int64_t n_vocab = vocab.n_tokens(); - const int64_t n_embd = hparams.n_embd_inp(); + const int64_t n_embd = ctx_type_to_embd_inp(hparams, cparams.ctx_type); // when computing embeddings, all tokens are output const bool output_all = cparams.embeddings; @@ -1710,6 +1807,20 @@ int llama_context::decode(const llama_batch & batch_inp) { embd_seq.clear(); output_swaps.clear(); + src_mctx_reset_on_exit decode_src_drop{&src_mctx_for_decode}; + if (src_ctx) { + auto * src_memory = src_ctx->get_memory(); + if (!src_memory) { + LLAMA_LOG_ERROR("%s: MTP source context has no memory module\n", __func__); + return -2; + } + src_mctx_for_decode = src_memory->init_full(); + if (!src_mctx_for_decode) { + LLAMA_LOG_ERROR("%s: failed to snapshot MTP source memory\n", __func__); + return -2; + } + } + sched_reserve(); bool did_optimize = false; @@ -1924,7 +2035,7 @@ int llama_context::decode(const llama_batch & batch_inp) { ggml_backend_t backend_h = ggml_backend_sched_get_tensor_backend(sched.get(), t_h_nextn); GGML_ASSERT(backend_h != nullptr); - const uint32_t n_embd = hparams.n_embd; + const uint32_t n_embd = hparams.n_embd_out(); float * embd_nextn_out = embd_nextn.data + offset*n_embd; GGML_ASSERT((offset + n_rows)*n_embd <= (int64_t) embd_nextn.size); @@ -2017,7 +2128,6 @@ uint32_t llama_context::output_reserve(int32_t n_outputs) { const auto n_batch = cparams.n_batch; const auto n_vocab = vocab.n_tokens(); - const auto n_embd = hparams.n_embd; const auto n_embd_out = hparams.n_embd_out(); bool has_logits = true; @@ -2036,12 +2146,12 @@ uint32_t llama_context::output_reserve(int32_t n_outputs) { logits.size = has_logits ? n_vocab*n_outputs_max : 0; embd.size = has_embd ? n_embd_out*n_outputs_max : 0; - embd_nextn.size = has_embd_nextn ? n_embd*n_outputs_max : 0; + embd_nextn.size = has_embd_nextn ? n_embd_out*n_outputs_max : 0; if (has_embd_nextn && !cparams.embeddings_nextn_masked) { // unmasked: nextn row exists for every token in the batch, not just // those flagged via batch.logits[i] -> size by token count instead. - embd_nextn.size = (size_t) n_embd * n_batch; + embd_nextn.size = (size_t) n_embd_out * n_batch; } // Allocate backend sampling output buffers if there are backend samplers configured. @@ -2304,6 +2414,8 @@ llm_graph_params llama_context::graph_params( /*.cvec =*/ cvec.get(), /*.loras =*/ loras.get(), /*.mctx =*/ mctx, + /*.src_mctx =*/ src_mctx_for_decode.get(), + /*.src_model =*/ src_ctx ? &src_ctx->get_model() : nullptr, /*.cross =*/ &cross, /*.samplers =*/ sampling.samplers, /*.n_outputs =*/ n_outputs, @@ -2351,7 +2463,7 @@ llm_graph_cb llama_context::graph_get_cb() const { // norm may be automatically assigned to the backend of the previous layer, increasing data transfer between backends // FIXME: fix in ggml_backend_sched - const bool full_offload = model.n_gpu_layers() > model.hparams.n_layer; + const bool full_offload = model.n_gpu_layers() > model.hparams.n_layer(); if (ubatch.n_tokens < 32 || full_offload) { if (il != -1 && strcmp(name, "norm") == 0) { const auto & dev_layer = model.dev_layer(il); @@ -3416,7 +3528,7 @@ llama_context * llama_init_from_model( if (params.flash_attn_type != LLAMA_FLASH_ATTN_TYPE_DISABLED && ggml_is_quantized(params.type_k)) { const uint32_t blck_size = ggml_blck_size(params.type_k); - for (uint32_t il = 0; il < model->hparams.n_layer; ++il) { + for (uint32_t il = 0; il < model->hparams.n_layer(); ++il) { if (model->hparams.n_embd_head_k(il) % blck_size != 0) { LLAMA_LOG_ERROR("%s: K cache type %s with block size %u does not divide n_embd_head_k=%u\n", __func__, ggml_type_name(params.type_k), blck_size, model->hparams.n_embd_head_k(il)); @@ -3427,7 +3539,7 @@ llama_context * llama_init_from_model( if (params.flash_attn_type != LLAMA_FLASH_ATTN_TYPE_DISABLED && ggml_is_quantized(params.type_v)) { const uint32_t blck_size = ggml_blck_size(params.type_v); - for (uint32_t il = 0; il < model->hparams.n_layer; ++il) { + for (uint32_t il = 0; il < model->hparams.n_layer(); ++il) { if (model->hparams.n_embd_head_v(il) % blck_size != 0) { LLAMA_LOG_ERROR("%s: V cache type %s with block size %u does not divide n_embd_head_v=%u\n", __func__, ggml_type_name(params.type_v), blck_size, model->hparams.n_embd_head_v(il)); @@ -3448,12 +3560,11 @@ llama_context * llama_init_from_model( model->hparams.pooling_type, params.pooling_type); } - if (params.ctx_type == LLAMA_CONTEXT_TYPE_MTP && - model->hparams.nextn_predict_layers == 0) { - LLAMA_LOG_WARN("%s: context type MTP requested but model doesn't contain MTP layers\n", __func__); - return nullptr; - } - + //if (params.ctx_type == LLAMA_CONTEXT_TYPE_MTP && + // model->hparams.n_layer_nextn == 0) { + // LLAMA_LOG_WARN("%s: context type MTP requested but model doesn't contain MTP layers\n", __func__); + // return nullptr; + //} try { auto * ctx = new llama_context(*model, params); @@ -3593,6 +3704,10 @@ void llama_set_embeddings_nextn(llama_context * ctx, bool value, bool masked) { ctx->set_embeddings_nextn(value, masked); } +void llama_set_mtp_source(llama_context * ctx, llama_context * src) { + ctx->set_mtp_source(src); +} + float * llama_get_embeddings_nextn(llama_context * ctx) { ctx->synchronize(); diff --git a/src/llama-context.h b/src/llama-context.h index 2af92b0f0968..935fa75af862 100644 --- a/src/llama-context.h +++ b/src/llama-context.h @@ -6,6 +6,7 @@ #include "llama-graph.h" #include "llama-adapter.h" #include "llama-impl.h" +#include "llama-memory.h" #include "ggml-cpp.h" #include "ggml-opt.h" @@ -111,6 +112,7 @@ struct llama_context { void set_embeddings (bool value); void set_embeddings_nextn(bool value, bool masked); + void set_mtp_source(llama_context * src); void set_causal_attn(bool value); void set_warmup(bool value); @@ -275,6 +277,12 @@ struct llama_context { std::unique_ptr memory; + // external KV source used by MTP draft contexts. src_ctx is the target + // context whose memory we read; src_mctx_for_decode is a per-decode + // snapshot held for the duration of one decode/sched_reserve call. + llama_context * src_ctx = nullptr; + llama_memory_context_ptr src_mctx_for_decode; + // decode output (2-dimensional array: [n_outputs][n_vocab]) buffer_view logits = {nullptr, 0}; diff --git a/src/llama-ext.h b/src/llama-ext.h index 7ad6125fad33..92f8bfffa494 100644 --- a/src/llama-ext.h +++ b/src/llama-ext.h @@ -93,6 +93,7 @@ LLAMA_API llama_memory_breakdown llama_get_memory_breakdown(const struct llama_c // If masked == true, output the embeddings only for the tokens with batch.logits != 0 // If masked == false, output the embeddings for all tokens in the batch regardless of batch.logits LLAMA_API void llama_set_embeddings_nextn(struct llama_context * ctx, bool value, bool masked); +LLAMA_API void llama_set_mtp_source(struct llama_context * ctx, struct llama_context * src); // mirrors: // LLAMA_API float * llama_get_embeddings(struct llama_context * ctx); diff --git a/src/llama-graph.cpp b/src/llama-graph.cpp index f910528d21b3..8bb28e696075 100644 --- a/src/llama-graph.cpp +++ b/src/llama-graph.cpp @@ -620,6 +620,35 @@ bool llm_graph_input_attn_kv_iswa::can_reuse(const llm_graph_params & params) { return res; } +void llm_graph_input_attn_src_kv_iswa::set_input(const llama_ubatch * ubatch) { + src_mctx->get_base()->set_input_kq_mask(self_kq_mask, ubatch, cparams.causal_attn); + src_mctx->get_swa() ->set_input_kq_mask(self_kq_mask_swa, ubatch, cparams.causal_attn); + + if (self_k_rot) { + src_mctx->get_base()->set_input_k_rot(self_k_rot); + } + if (self_v_rot) { + src_mctx->get_base()->set_input_v_rot(self_v_rot); + } + if (self_k_rot_swa) { + src_mctx->get_swa()->set_input_k_rot(self_k_rot_swa); + } + if (self_v_rot_swa) { + src_mctx->get_swa()->set_input_v_rot(self_v_rot_swa); + } +} + +bool llm_graph_input_attn_src_kv_iswa::can_reuse(const llm_graph_params & params) { + const auto * mctx = static_cast(params.src_mctx); + + this->src_mctx = mctx; + + bool res = true; + res &= can_reuse_kq_mask(self_kq_mask, mctx->get_base(), params.ubatch, params.cparams); + res &= can_reuse_kq_mask(self_kq_mask_swa, mctx->get_swa(), params.ubatch, params.cparams); + return res; +} + void llm_graph_input_attn_cross::set_input(const llama_ubatch * ubatch) { GGML_ASSERT(cross_kq_mask); @@ -1005,7 +1034,7 @@ llm_graph_context::llm_graph_context(const llm_graph_params & params) : cparams (params.cparams), ubatch (params.ubatch), n_embd (hparams.n_embd), - n_layer (hparams.n_layer), + n_layer (hparams.n_layer()), n_rot (hparams.n_rot()), n_ctx (cparams.n_ctx), n_head (hparams.n_head()), @@ -1034,6 +1063,8 @@ llm_graph_context::llm_graph_context(const llm_graph_params & params) : cvec (params.cvec), loras (params.loras), mctx (params.mctx), + src_mctx (params.src_mctx), + src_model (params.src_model), cross (params.cross), samplers (params.samplers), cb_func (params.cb), @@ -2604,6 +2635,98 @@ llm_graph_input_attn_cross * llm_graph_context::build_attn_inp_cross() const { return (llm_graph_input_attn_cross *) res->add_input(std::move(inp)); } +llm_graph_input_attn_src_kv_iswa * llm_graph_context::build_attn_inp_src_kv_iswa() const { + GGML_ASSERT(src_mctx && "MTP draft graph requires src_mctx (set via llama_set_mtp_source)"); + + const auto * src_iswa = static_cast(src_mctx); + + auto inp = std::make_unique(hparams, cparams, src_iswa); + + inp->self_kq_mask = build_attn_inp_kq_mask(ctx0, src_iswa->get_base(), ubatch, cparams); + inp->self_kq_mask_cnv = cparams.flash_attn ? ggml_cast(ctx0, inp->self_kq_mask, GGML_TYPE_F16) : inp->self_kq_mask; + + inp->self_kq_mask_swa = build_attn_inp_kq_mask(ctx0, src_iswa->get_swa(), ubatch, cparams); + inp->self_kq_mask_swa_cnv = cparams.flash_attn ? ggml_cast(ctx0, inp->self_kq_mask_swa, GGML_TYPE_F16) : inp->self_kq_mask_swa; + + inp->self_k_rot = src_iswa->get_base()->build_input_k_rot(ctx0); + inp->self_v_rot = src_iswa->get_base()->build_input_v_rot(ctx0); + inp->self_k_rot_swa = src_iswa->get_swa()->build_input_k_rot(ctx0); + inp->self_v_rot_swa = src_iswa->get_swa()->build_input_v_rot(ctx0); + + return (llm_graph_input_attn_src_kv_iswa *) res->add_input(std::move(inp)); +} + +ggml_tensor * llm_graph_context::build_attn( + llm_graph_input_attn_src_kv_iswa * inp, + ggml_tensor * wo, + ggml_tensor * wo_b, + ggml_tensor * wo_s, + ggml_tensor * q_cur, + ggml_tensor * kq_b, + ggml_tensor * sinks, + ggml_tensor * v_mla, + float kq_scale, + int il_assist, + int il_src) const { + const bool is_swa = hparams.is_swa(il_assist); + + const auto * src_iswa = inp->src_mctx; + const auto * src_cur = is_swa ? src_iswa->get_swa() : src_iswa->get_base(); + + const auto & kq_mask = is_swa ? inp->get_kq_mask_swa() : inp->get_kq_mask(); + + auto * k_rot = is_swa ? inp->self_k_rot_swa : inp->self_k_rot; + auto * v_rot = is_swa ? inp->self_v_rot_swa : inp->self_v_rot; + + if (k_rot) { + q_cur = ggml_mul_mat_aux(ctx0, q_cur, k_rot); + } + + ggml_build_forward_expand(gf, q_cur); + + ggml_tensor * q = q_cur; + ggml_tensor * k = src_cur->get_k(ctx0, il_src); + ggml_tensor * v = src_cur->get_v(ctx0, il_src); + + // build_attn_mha splits q across k->ne[3] (the trunk's stream count). When the + // trunk runs kv_unified=false the assistant's ubatch only references a subset + // of streams (one per active draft seq); q->ne[2] is not divisible by the full + // n_stream and the view collapses tokens. Slice k/v down to exactly the streams + // referenced by this ubatch. Requires those streams to form a contiguous range. + if (k->ne[3] > 1 && (uint32_t) k->ne[3] != ubatch.n_seqs_unq) { + GGML_ASSERT(ubatch.n_seqs_unq > 0 && ubatch.seq_id_unq); + llama_seq_id min_s = ubatch.seq_id_unq[0]; + llama_seq_id max_s = ubatch.seq_id_unq[0]; + for (uint32_t s = 1; s < ubatch.n_seqs_unq; ++s) { + min_s = std::min(min_s, ubatch.seq_id_unq[s]); + max_s = std::max(max_s, ubatch.seq_id_unq[s]); + } + GGML_ASSERT((uint32_t)(max_s - min_s + 1) == ubatch.n_seqs_unq && + "MTP src-kv attn requires the active draft seq_ids to be contiguous"); + GGML_ASSERT((int64_t) max_s < k->ne[3] && "MTP assistant seq_id beyond trunk stream count"); + + k = ggml_view_4d(ctx0, k, k->ne[0], k->ne[1], k->ne[2], (int64_t) ubatch.n_seqs_unq, + k->nb[1], k->nb[2], k->nb[3], (size_t) min_s * k->nb[3]); + v = ggml_view_4d(ctx0, v, v->ne[0], v->ne[1], v->ne[2], (int64_t) ubatch.n_seqs_unq, + v->nb[1], v->nb[2], v->nb[3], (size_t) min_s * v->nb[3]); + } + + ggml_tensor * cur = build_attn_mha(q, k, v, kq_b, kq_mask, sinks, v_mla, kq_scale, il_assist); + cb(cur, "kqv_out", il_assist); + + if (v_rot) { + cur = ggml_mul_mat_aux(ctx0, cur, v_rot); + } + + if (wo) { + cur = build_lora_mm(wo, cur, wo_s); + } + if (wo_b) { + cur = ggml_add(ctx0, cur, wo_b); + } + return cur; +} + ggml_tensor * llm_graph_context::build_attn( llm_graph_input_attn_cross * inp, ggml_tensor * wo, diff --git a/src/llama-graph.h b/src/llama-graph.h index bf5be09ac7fa..8d6b88fe012a 100644 --- a/src/llama-graph.h +++ b/src/llama-graph.h @@ -459,6 +459,42 @@ class llm_graph_input_attn_kv_iswa : public llm_graph_input_i { const llama_kv_cache_iswa_context * mctx; }; +// mask-only input for attention against an external (read-only) ISWA KV cache. +// used by MTP draft graphs that attend to the target's KV without owning any. +class llm_graph_input_attn_src_kv_iswa : public llm_graph_input_i { +public: + llm_graph_input_attn_src_kv_iswa( + const llama_hparams & hparams, + const llama_cparams & cparams, + const llama_kv_cache_iswa_context * src_mctx) : + hparams(hparams), + cparams(cparams), + src_mctx(src_mctx) { + } + ~llm_graph_input_attn_src_kv_iswa() = default; + + void set_input(const llama_ubatch * ubatch) override; + bool can_reuse(const llm_graph_params & params) override; + + ggml_tensor * get_kq_mask() const { return self_kq_mask_cnv; } + ggml_tensor * get_kq_mask_swa() const { return self_kq_mask_swa_cnv; } + + ggml_tensor * self_kq_mask = nullptr; + ggml_tensor * self_kq_mask_cnv = nullptr; + ggml_tensor * self_kq_mask_swa = nullptr; + ggml_tensor * self_kq_mask_swa_cnv = nullptr; + + ggml_tensor * self_k_rot = nullptr; + ggml_tensor * self_v_rot = nullptr; + ggml_tensor * self_k_rot_swa = nullptr; + ggml_tensor * self_v_rot_swa = nullptr; + + const llama_hparams hparams; + const llama_cparams cparams; + + const llama_kv_cache_iswa_context * src_mctx; +}; + class llm_graph_input_attn_cross : public llm_graph_input_i { public: llm_graph_input_attn_cross(const llama_cross * cross) : cross(cross) {} @@ -601,6 +637,11 @@ struct llm_graph_params { const llama_adapter_cvec * cvec; const llama_adapter_loras * loras; const llama_memory_context_i * mctx; + // per-decode snapshot of an external memory module the graph reads from + // (never writes) — e.g. ctx_dft reading target KV during MTP draft. + // nullptr for a main decode. Rebound inside reuse-aware input classes. + const llama_memory_context_i * src_mctx; + const llama_model * src_model; const llama_cross * cross; std::map samplers; @@ -818,6 +859,8 @@ struct llm_graph_context { const llama_adapter_cvec * cvec; const llama_adapter_loras * loras; const llama_memory_context_i * mctx; + const llama_memory_context_i * src_mctx; + const llama_model * src_model; const llama_cross * cross; std::map samplers; @@ -1047,6 +1090,24 @@ struct llm_graph_context { float kq_scale, int il) const; + llm_graph_input_attn_src_kv_iswa * build_attn_inp_src_kv_iswa() const; + + // Q-only attention against an external ISWA KV cache (no K/V projections, + // no writes). il_assist labels the attention block in the local graph for + // logging; il_src indexes the source K/V layer to attend to. + ggml_tensor * build_attn( + llm_graph_input_attn_src_kv_iswa * inp, + ggml_tensor * wo, + ggml_tensor * wo_b, + ggml_tensor * wo_s, + ggml_tensor * q_cur, // [n_embd_head_q, n_head_q, n_tokens] + ggml_tensor * kq_b, + ggml_tensor * sinks, // [n_head_q] + ggml_tensor * v_mla, // [n_embd_head_v_mla, n_embd_head_v, n_head_v] + float kq_scale, + int il_assist, + int il_src) const; + llm_graph_input_attn_cross * build_attn_inp_cross() const; ggml_tensor * build_attn( diff --git a/src/llama-hparams.cpp b/src/llama-hparams.cpp index 087afec55c60..e1e49d1cc1fe 100644 --- a/src/llama-hparams.cpp +++ b/src/llama-hparams.cpp @@ -7,31 +7,38 @@ void llama_hparams::set_swa_pattern(uint32_t n_pattern, bool dense_first) { if (dense_first) { - for (uint32_t il = 0; il < n_layer; ++il) { + for (uint32_t il = 0; il < n_layer(); ++il) { is_swa_impl[il] = n_pattern == 0 || (il % n_pattern != 0); } } else { - for (uint32_t il = 0; il < n_layer; ++il) { + for (uint32_t il = 0; il < n_layer(); ++il) { is_swa_impl[il] = n_pattern == 0 || (il % n_pattern < (n_pattern - 1)); } } + + for (uint32_t il = n_layer(); il < n_layer_all; ++il) { + is_swa_impl[il] = false; + } } -// TODO: implement -//void llama_hparams::set_recr_pattern(uint32_t n_pattern, bool dense_first) { -// if (dense_first) { -// for (uint32_t il = 0; il < n_layer; ++il) { -// is_recr_impl[il] = n_pattern == 0 || (il % n_pattern != 0); -// } -// } else { -// for (uint32_t il = 0; il < n_layer; ++il) { -// is_recr_impl[il] = n_pattern == 0 || (il % n_pattern < (n_pattern - 1)); -// } -// } -//} +void llama_hparams::set_recr_pattern(uint32_t n_pattern, bool dense_first) { + if (dense_first) { + for (uint32_t il = 0; il < n_layer(); ++il) { + is_recr_impl[il] = n_pattern == 0 || (il % n_pattern != 0); + } + } else { + for (uint32_t il = 0; il < n_layer(); ++il) { + is_recr_impl[il] = n_pattern == 0 || (il % n_pattern < (n_pattern - 1)); + } + } + + for (uint32_t il = n_layer(); il < n_layer_all; ++il) { + is_recr_impl[il] = false; + } +} bool llama_hparams::is_swa_any() const { - for (uint32_t il = 0; il < n_layer; ++il) { + for (uint32_t il = 0; il < n_layer_all; ++il) { if (is_swa_impl[il]) { return true; } @@ -41,7 +48,7 @@ bool llama_hparams::is_swa_any() const { } uint32_t llama_hparams::n_head(uint32_t il) const { - if (il < n_layer) { + if (il < n_layer_all) { return n_head_arr[il]; } @@ -49,7 +56,7 @@ uint32_t llama_hparams::n_head(uint32_t il) const { } uint32_t llama_hparams::n_head_kv(uint32_t il) const { - if (il < n_layer) { + if (il < n_layer_all) { return n_head_kv_arr[il]; } @@ -57,7 +64,7 @@ uint32_t llama_hparams::n_head_kv(uint32_t il) const { } uint32_t llama_hparams::n_ff(uint32_t il) const { - if (il < n_layer) { + if (il < n_layer_all) { return n_ff_arr[il]; } @@ -76,7 +83,7 @@ uint32_t llama_hparams::n_gqa(uint32_t il) const { } uint32_t llama_hparams::n_rot(uint32_t il) const { - if (il < n_layer) { + if (il < n_layer_all) { return is_swa(il) ? n_rot_swa : n_rot_full; } @@ -98,7 +105,7 @@ uint32_t llama_hparams::n_embd_out() const { } uint32_t llama_hparams::n_embd_head_k(uint32_t il) const { - if (il < n_layer) { + if (il < n_layer_all) { return is_swa(il) ? n_embd_head_k_swa : n_embd_head_k_full; } @@ -106,7 +113,7 @@ uint32_t llama_hparams::n_embd_head_k(uint32_t il) const { } uint32_t llama_hparams::n_embd_head_v(uint32_t il) const { - if (il < n_layer) { + if (il < n_layer_all) { return is_swa(il) ? n_embd_head_v_swa : n_embd_head_v_full; } @@ -127,7 +134,7 @@ uint32_t llama_hparams::n_embd_v_gqa(uint32_t il) const { bool llama_hparams::is_n_embd_k_gqa_variable() const { const uint32_t val = n_embd_k_gqa(); - for (uint32_t il = 0; il < n_layer; ++il) { + for (uint32_t il = 0; il < n_layer_all; ++il) { if (val != n_embd_k_gqa(il)) { return true; } @@ -138,7 +145,7 @@ bool llama_hparams::is_n_embd_k_gqa_variable() const { bool llama_hparams::is_n_embd_v_gqa_variable() const { const uint32_t val = n_embd_v_gqa(); - for (uint32_t il = 0; il < n_layer; ++il) { + for (uint32_t il = 0; il < n_layer_all; ++il) { if (val != n_embd_v_gqa(il)) { return true; } @@ -149,7 +156,7 @@ bool llama_hparams::is_n_embd_v_gqa_variable() const { uint32_t llama_hparams::n_embd_k_gqa_max() const { uint32_t val = n_embd_k_gqa(); - for (uint32_t il = 0; il < n_layer; ++il) { + for (uint32_t il = 0; il < n_layer_all; ++il) { val = std::max(val, n_embd_k_gqa(il)); } @@ -158,7 +165,7 @@ uint32_t llama_hparams::n_embd_k_gqa_max() const { uint32_t llama_hparams::n_embd_v_gqa_max() const { uint32_t val = n_embd_v_gqa(); - for (uint32_t il = 0; il < n_layer; ++il) { + for (uint32_t il = 0; il < n_layer_all; ++il) { val = std::max(val, n_embd_v_gqa(il)); } @@ -207,11 +214,11 @@ uint32_t llama_hparams::n_embd_s() const { } bool llama_hparams::is_recr(uint32_t il) const { - if (il < n_layer) { + if (il < n_layer_all) { return is_recr_impl[il]; } - GGML_ABORT("%s: il (%u) out of bounds (n_layer: %u)\n", __func__, il, n_layer); + GGML_ABORT("%s: il (%u) out of bounds (n_layer_all: %u)\n", __func__, il, n_layer_all); } uint32_t llama_hparams::n_pos_per_embd() const { @@ -219,11 +226,11 @@ uint32_t llama_hparams::n_pos_per_embd() const { } bool llama_hparams::is_swa(uint32_t il) const { - if (il < n_layer) { + if (il < n_layer_all) { return is_swa_impl[il]; } - GGML_ABORT("fatal error"); + GGML_ABORT("%s: il (%u) out of bounds (n_layer_all: %u)\n", __func__, il, n_layer_all); } bool llama_hparams::is_mla() const { @@ -242,12 +249,6 @@ uint32_t llama_hparams::n_embd_head_v_mla() const { } bool llama_hparams::has_kv(uint32_t il) const { - if (kv_only_nextn) { - // MTP head: only the trailing nextn_predict_layers blocks own a KV cache; - // the leading trunk blocks are not executed in this graph. - return nextn_predict_layers > 0 && il >= (n_layer - nextn_predict_layers); - } - if (n_layer_kv_from_start >= 0) { if (il < (uint32_t) n_layer_kv_from_start) { return true; @@ -260,16 +261,8 @@ bool llama_hparams::has_kv(uint32_t il) const { return true; } -uint32_t llama_hparams::n_layer_kv() const { - uint32_t res = 0; - - for (uint32_t il = 0; il < n_layer; ++il) { - if (has_kv(il)) { - res++; - } - } - - return res; +uint32_t llama_hparams::n_layer() const { + return n_layer_all - n_layer_nextn; } bool llama_hparams::use_mrope() const { diff --git a/src/llama-hparams.h b/src/llama-hparams.h index e8ed4dd74de3..fde6183e8786 100644 --- a/src/llama-hparams.h +++ b/src/llama-hparams.h @@ -48,12 +48,15 @@ struct llama_hparams { uint32_t n_ctx_train; // context size the model was trained on uint32_t n_embd; - uint32_t n_layer; - int32_t n_layer_kv_from_start = -1; // if non-negative, the first n_layer_kv_from_start layers have KV cache + uint32_t n_layer_all; + uint32_t n_layer_nextn = 0; uint32_t n_expert = 0; uint32_t n_expert_used = 0; uint32_t n_rel_attn_bkts = 0; + // TODO: this needs to be reworked + int32_t n_layer_kv_from_start = -1; // if non-negative, the first n_layer_kv_from_start layers have KV cache + // different head size for full_attention and SWA layers uint32_t n_embd_head_k_full; // dimension of keys (d_k). d_q is assumed to be the same, but there are n_head q heads, and only n_head_kv k-v heads uint32_t n_embd_head_v_full; // dimension of values (d_v) aka n_embd_head @@ -96,9 +99,6 @@ struct llama_hparams { uint32_t expert_gating_func = LLAMA_EXPERT_GATING_FUNC_TYPE_NONE; uint32_t moe_every_n_layers = 0; uint32_t moe_latent_size = 0; - uint32_t nextn_predict_layers = 0; - - bool kv_only_nextn = false; // if true, only the last nextn_predict_layers blocks have a KV cache (MTP head arches) float f_norm_eps; float f_norm_rms_eps; @@ -272,8 +272,7 @@ struct llama_hparams { bool is_swa(uint32_t il) const; - // TODO: implement - //void set_recr_pattern(uint32_t n_pattern, bool dense_first = false); + void set_recr_pattern(uint32_t n_pattern, bool dense_first = false); // whether or not the given layer is recurrent (for hybrid models) bool is_recr(uint32_t il) const; @@ -329,8 +328,8 @@ struct llama_hparams { bool has_kv(uint32_t il) const; - // number of layers for which has_kv() returns true - uint32_t n_layer_kv() const; + // number of effective layers (excludes nextn layers) + uint32_t n_layer() const; // note that this function uses different SWA parameters from those in the hparams // note: inlined on purpose for performance reasons diff --git a/src/llama-kv-cache.cpp b/src/llama-kv-cache.cpp index 82da38e0b611..4bbec21a8a20 100644 --- a/src/llama-kv-cache.cpp +++ b/src/llama-kv-cache.cpp @@ -97,7 +97,7 @@ llama_kv_cache::llama_kv_cache( GGML_ASSERT(kv_size % n_pad == 0); - const uint32_t n_layer_kv = hparams.n_layer_kv(); + const uint32_t n_layer = hparams.n_layer_all; // define a comparator for the buft -> ctx map to ensure that the order is well-defined: struct ggml_backend_buft_comparator { @@ -112,7 +112,7 @@ llama_kv_cache::llama_kv_cache( auto it = ctx_map.find(buft); if (it == ctx_map.end()) { ggml_init_params params = { - /*.mem_size =*/ size_t(2u*(1 + n_stream)*n_layer_kv*ggml_tensor_overhead()), + /*.mem_size =*/ size_t(2u*(1 + n_stream)*n_layer*ggml_tensor_overhead()), /*.mem_buffer =*/ NULL, /*.no_alloc =*/ true, }; @@ -160,7 +160,7 @@ llama_kv_cache::llama_kv_cache( const bool is_mla = hparams.is_mla(); - for (uint32_t il = 0; il < hparams.n_layer; il++) { + for (uint32_t il = 0; il < n_layer; il++) { if (!hparams.has_kv(il)) { LLAMA_LOG_DEBUG("%s: layer %3d: does not have KV cache\n", __func__, il); continue; @@ -230,7 +230,7 @@ llama_kv_cache::llama_kv_cache( if (reuse) { LLAMA_LOG_DEBUG("%s: reusing layers:\n", __func__); - for (uint32_t il = 0; il < hparams.n_layer; il++) { + for (uint32_t il = 0; il < n_layer; il++) { const int32_t il_reuse = reuse(il); if (il_reuse < 0) { @@ -2462,6 +2462,10 @@ uint32_t llama_kv_cache_context::get_n_kv() const { return n_kv; } +llama_pos llama_kv_cache_context::seq_pos_max(llama_seq_id seq_id) const { + return kv->seq_pos_max(seq_id); +} + ggml_type llama_kv_cache_context::type_k() const { return kv->type_k(); } diff --git a/src/llama-kv-cache.h b/src/llama-kv-cache.h index 649269af6dd4..99f501019569 100644 --- a/src/llama-kv-cache.h +++ b/src/llama-kv-cache.h @@ -354,6 +354,11 @@ class llama_kv_cache_context : public llama_memory_context_i { uint32_t get_n_kv() const; + // last position recorded in the cache for this sequence; -1 if absent. + // exposed for cross-context KV consumers (e.g. MTP draft) that need to + // anchor the source position without owning a memory module of their own. + llama_pos seq_pos_max(llama_seq_id seq_id) const; + ggml_type type_k() const; ggml_type type_v() const; diff --git a/src/llama-memory-recurrent.cpp b/src/llama-memory-recurrent.cpp index ec5dc5835dd4..6a4892fb471d 100644 --- a/src/llama-memory-recurrent.cpp +++ b/src/llama-memory-recurrent.cpp @@ -26,7 +26,7 @@ llama_memory_recurrent::llama_memory_recurrent( uint32_t n_seq_max, uint32_t n_rs_seq, const layer_filter_cb & filter) : hparams(model.hparams), n_seq_max(n_seq_max) { - const int32_t n_layer = hparams.n_layer; + const int32_t n_layer = hparams.n_layer(); head = 0; size = mem_size; @@ -863,7 +863,7 @@ void llama_memory_recurrent::state_write_meta(llama_io_write_i & io, const std:: void llama_memory_recurrent::state_write_data(llama_io_write_i & io, const std::vector> & cell_ranges) const { const uint32_t s_trans = 0; - const uint32_t n_layer = hparams.n_layer; + const uint32_t n_layer = hparams.n_layer(); io.write(&s_trans, sizeof(s_trans)); io.write(&n_layer, sizeof(n_layer)); @@ -1047,8 +1047,8 @@ bool llama_memory_recurrent::state_read_data(llama_io_read_i & io, uint32_t cell io.read(&s_trans, sizeof(s_trans)); io.read(&n_layer, sizeof(n_layer)); - if (n_layer != hparams.n_layer) { - LLAMA_LOG_ERROR("%s: mismatched layer count (%u instead of %u)\n", __func__, n_layer, hparams.n_layer); + if (n_layer != hparams.n_layer()) { + LLAMA_LOG_ERROR("%s: mismatched layer count (%u instead of %u)\n", __func__, n_layer, hparams.n_layer()); return false; } if (cell_count > size) { diff --git a/src/llama-model-loader.cpp b/src/llama-model-loader.cpp index 4d7b11067c97..ba08a19ac76a 100644 --- a/src/llama-model-loader.cpp +++ b/src/llama-model-loader.cpp @@ -1050,10 +1050,10 @@ struct ggml_tensor * llama_model_loader::create_tensor( if (it == ctx_map.end()) { // one ggml context per buffer type int max_n_tensors = n_tensors; - max_n_tensors += 1; // duplicated output tensor - max_n_tensors += hparams.n_layer*2; // duplicated rope freq tensors + max_n_tensors += 1; // duplicated output tensor + max_n_tensors += hparams.n_layer()*2; // duplicated rope freq tensors if (files.empty()) { - max_n_tensors += hparams.n_layer*256; // this should be well above what any model actually uses + max_n_tensors += hparams.n_layer()*256; // this should be well above what any model actually uses } const size_t ctx_size = ggml_tensor_overhead()*max_n_tensors; diff --git a/src/llama-model-saver.cpp b/src/llama-model-saver.cpp index 26fda1abfae6..b05228780905 100644 --- a/src/llama-model-saver.cpp +++ b/src/llama-model-saver.cpp @@ -77,7 +77,7 @@ void llama_model_saver::add_kv(const enum llm_kv key, const char value) { template void llama_model_saver::add_kv(const enum llm_kv key, const Container & value, const bool per_layer) { GGML_ASSERT(model != nullptr || !per_layer); - const size_t n_values = per_layer ? size_t(model->hparams.n_layer) : value.size(); + const size_t n_values = per_layer ? size_t(model->hparams.n_layer()) : value.size(); GGML_ASSERT(n_values <= value.size()); if (n_values == 0) { @@ -206,7 +206,7 @@ void llama_model_saver::add_kv_from_model() { if (hparams.n_embd_out_impl > 0) { add_kv(LLM_KV_EMBEDDING_LENGTH_OUT, hparams.n_embd_out_impl); } - add_kv(LLM_KV_BLOCK_COUNT, hparams.n_layer); + add_kv(LLM_KV_BLOCK_COUNT, hparams.n_layer_all); add_kv(LLM_KV_LEADING_DENSE_BLOCK_COUNT, hparams.n_layer_dense_lead); add_kv(LLM_KV_FEED_FORWARD_LENGTH, hparams.n_ff_arr, true); add_kv(LLM_KV_EXPERT_FEED_FORWARD_LENGTH, hparams.n_ff_exp); @@ -227,7 +227,7 @@ void llama_model_saver::add_kv_from_model() { add_kv(LLM_KV_EXPERT_GROUP_SCALE, hparams.expert_group_scale); add_kv(LLM_KV_EXPERTS_PER_GROUP, hparams.n_group_experts); add_kv(LLM_KV_MOE_EVERY_N_LAYERS, hparams.moe_every_n_layers); - add_kv(LLM_KV_NEXTN_PREDICT_LAYERS, hparams.nextn_predict_layers); + add_kv(LLM_KV_NEXTN_PREDICT_LAYERS, hparams.n_layer_nextn); add_kv(LLM_KV_NUM_DEEPSTACK_LAYERS, hparams.n_deepstack_layers); add_kv(LLM_KV_POOLING_TYPE, uint32_t(hparams.pooling_type)); add_kv(LLM_KV_LOGIT_SCALE, hparams.f_logit_scale); diff --git a/src/llama-model.cpp b/src/llama-model.cpp index bc7a83b15f53..fe64c70d358a 100644 --- a/src/llama-model.cpp +++ b/src/llama-model.cpp @@ -139,6 +139,8 @@ static llama_model * llama_model_mapping(llm_arch arch, const llama_model_params return new llama_model_gemma3n(params); case LLM_ARCH_GEMMA4: return new llama_model_gemma4(params); + case LLM_ARCH_GEMMA4_ASSISTANT: + return new llama_model_gemma4_assistant(params); case LLM_ARCH_GEMMA_EMBEDDING: return new llama_model_gemma_embedding(params); case LLM_ARCH_STARCODER2: @@ -398,7 +400,7 @@ struct ggml_backend_meta_split_state llama_meta_device_get_split_state(const str rotation = get_il_eff(il) % ud->n_devices; } else { il = 0; - rotation = hparams.n_layer % ud->n_devices; + rotation = hparams.n_layer() % ud->n_devices; } const ggml_tensor * tensor_axis_0 = suffix.empty() ? tensor : ud->model->get_tensor((prefix + suffix).c_str()); if (tensor_axis_0 == nullptr) { @@ -1034,7 +1036,7 @@ void llama_model_base::load_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_EMBEDDING_LENGTH_OUT, hparams.n_embd_out_impl, false); ml.get_key(LLM_KV_ATTENTION_CAUSAL, hparams.causal_attn, false); ml.get_key(LLM_KV_POOLING_TYPE, hparams.pooling_type, false); - ml.get_key(LLM_KV_BLOCK_COUNT, hparams.n_layer); + ml.get_key(LLM_KV_BLOCK_COUNT, hparams.n_layer_all); ml.get_key(LLM_KV_EXPERT_COUNT, hparams.n_expert, false); ml.get_key(LLM_KV_EXPERT_USED_COUNT, hparams.n_expert_used, false); ml.get_key(LLM_KV_EXPERT_GROUP_COUNT, hparams.n_expert_groups, false); @@ -1089,13 +1091,13 @@ void llama_model_base::load_hparams(llama_model_loader & ml) { std::fill(hparams.swiglu_clamp_exp.begin(), hparams.swiglu_clamp_exp.end(), 0.0f); std::fill(hparams.swiglu_clamp_shexp.begin(), hparams.swiglu_clamp_shexp.end(), 0.0f); - ml.get_key_or_arr(LLM_KV_FEED_FORWARD_LENGTH, hparams.n_ff_arr, hparams.n_layer, false); - ml.get_key_or_arr(LLM_KV_ATTENTION_HEAD_COUNT, hparams.n_head_arr, hparams.n_layer, false); + ml.get_key_or_arr(LLM_KV_FEED_FORWARD_LENGTH, hparams.n_ff_arr, hparams.n_layer(), false); + ml.get_key_or_arr(LLM_KV_ATTENTION_HEAD_COUNT, hparams.n_head_arr, hparams.n_layer(), false); // n_head_kv is optional, default to n_head hparams.n_head_kv_arr = hparams.n_head_arr; - ml.get_key_or_arr(LLM_KV_ATTENTION_HEAD_COUNT_KV, hparams.n_head_kv_arr, hparams.n_layer, false); + ml.get_key_or_arr(LLM_KV_ATTENTION_HEAD_COUNT_KV, hparams.n_head_kv_arr, hparams.n_layer(), false); bool rope_finetuned = false; ml.get_key(LLM_KV_ROPE_SCALING_FINETUNED, rope_finetuned, false); @@ -1194,7 +1196,7 @@ bool llama_model_base::load_tensors(llama_model_loader & ml) { const auto & use_mlock = params.use_mlock; const auto & tensor_split = params.tensor_split; - const int n_layer = hparams.n_layer; + const int n_layer = hparams.n_layer_all; const int n_gpu_layers = this->n_gpu_layers(); const bool use_mmap_buffer = true; @@ -1251,10 +1253,10 @@ bool llama_model_base::load_tensors(llama_model_loader & ml) { splits[i] /= split_sum; } - const int i_gpu_start = std::max(int(hparams.n_layer) + 1 - n_gpu_layers, 0); - const int act_gpu_layers = devices.empty() ? 0 : std::min(n_gpu_layers, int(n_layer) + 1); + const int i_gpu_start = std::max(n_layer + 1 - n_gpu_layers, 0); + const int act_gpu_layers = devices.empty() ? 0 : std::min(n_gpu_layers, n_layer + 1); auto get_layer_buft_list = [&](int il) -> llama_model::impl::layer_dev { - const bool is_swa = il < int(hparams.n_layer) && hparams.is_swa(il); + const bool is_swa = il < n_layer && hparams.is_swa(il); if (il < i_gpu_start || (il - i_gpu_start) >= act_gpu_layers) { LLAMA_LOG_DEBUG("load_tensors: layer %3d assigned to device %s, is_swa = %d\n", il, ggml_backend_dev_name(cpu_dev), is_swa); return {cpu_dev, &pimpl->cpu_buft_list}; @@ -1557,7 +1559,7 @@ bool llama_model_base::load_tensors(llama_model_loader & ml) { } if (llama_supports_gpu_offload()) { - const int n_gpu = std::min(n_gpu_layers, int(hparams.n_layer)); + const int n_gpu = std::min(n_gpu_layers, n_layer); int n_repeating = n_gpu; if (n_repeating > 0) { @@ -1566,8 +1568,8 @@ bool llama_model_base::load_tensors(llama_model_loader & ml) { } LLAMA_LOG_INFO("%s: offloading %d repeating layers to GPU\n", __func__, n_repeating); - const int max_backend_supported_layers = hparams.n_layer + 1; - const int max_offloadable_layers = hparams.n_layer + 1; + const int max_backend_supported_layers = n_layer + 1; + const int max_offloadable_layers = n_layer + 1; LLAMA_LOG_INFO("%s: offloaded %d/%d layers to GPU\n", __func__, std::min(n_gpu_layers, max_offloadable_layers), max_backend_supported_layers); } @@ -1636,7 +1638,7 @@ const float * llama_model::tensor_split() const { } uint32_t llama_model::n_gpu_layers() const { - return params.n_gpu_layers >= 0 ? params.n_gpu_layers : hparams.n_layer + 1; + return params.n_gpu_layers >= 0 ? params.n_gpu_layers : hparams.n_layer() + 1; } llama_split_mode llama_model::split_mode() const { @@ -1707,17 +1709,17 @@ void llama_model::print_info() const { LLAMA_LOG_INFO("%s: n_ctx_train = %u\n", __func__, hparams.n_ctx_train); LLAMA_LOG_INFO("%s: n_embd = %u\n", __func__, hparams.n_embd); LLAMA_LOG_INFO("%s: n_embd_inp = %u\n", __func__, hparams.n_embd_inp()); - LLAMA_LOG_INFO("%s: n_layer = %u\n", __func__, hparams.n_layer); - LLAMA_LOG_INFO("%s: n_head = %s\n", __func__, print_f([&](uint32_t il) { return hparams.n_head(il); }, hparams.n_layer).c_str()); - LLAMA_LOG_INFO("%s: n_head_kv = %s\n", __func__, print_f([&](uint32_t il) { return hparams.n_head_kv(il); }, hparams.n_layer).c_str()); + LLAMA_LOG_INFO("%s: n_layer = %u\n", __func__, hparams.n_layer()); + LLAMA_LOG_INFO("%s: n_head = %s\n", __func__, print_f([&](uint32_t il) { return hparams.n_head(il); }, hparams.n_layer()).c_str()); + LLAMA_LOG_INFO("%s: n_head_kv = %s\n", __func__, print_f([&](uint32_t il) { return hparams.n_head_kv(il); }, hparams.n_layer()).c_str()); LLAMA_LOG_INFO("%s: n_rot = %u\n", __func__, hparams.n_rot_full); LLAMA_LOG_INFO("%s: n_swa = %u\n", __func__, hparams.n_swa); LLAMA_LOG_INFO("%s: is_swa_any = %u\n", __func__, hparams.is_swa_any()); LLAMA_LOG_INFO("%s: n_embd_head_k = %u\n", __func__, hparams.n_embd_head_k_full); LLAMA_LOG_INFO("%s: n_embd_head_v = %u\n", __func__, hparams.n_embd_head_v_full); - LLAMA_LOG_INFO("%s: n_gqa = %s\n", __func__, print_f([&](uint32_t il) { return hparams.n_gqa(il); }, hparams.n_layer).c_str()); - LLAMA_LOG_INFO("%s: n_embd_k_gqa = %s\n", __func__, print_f([&](uint32_t il) { return hparams.n_embd_k_gqa(il); }, hparams.n_layer).c_str()); - LLAMA_LOG_INFO("%s: n_embd_v_gqa = %s\n", __func__, print_f([&](uint32_t il) { return hparams.n_embd_v_gqa(il); }, hparams.n_layer).c_str()); + LLAMA_LOG_INFO("%s: n_gqa = %s\n", __func__, print_f([&](uint32_t il) { return hparams.n_gqa(il); }, hparams.n_layer()).c_str()); + LLAMA_LOG_INFO("%s: n_embd_k_gqa = %s\n", __func__, print_f([&](uint32_t il) { return hparams.n_embd_k_gqa(il); }, hparams.n_layer()).c_str()); + LLAMA_LOG_INFO("%s: n_embd_v_gqa = %s\n", __func__, print_f([&](uint32_t il) { return hparams.n_embd_v_gqa(il); }, hparams.n_layer()).c_str()); LLAMA_LOG_INFO("%s: f_norm_eps = %.1e\n", __func__, hparams.f_norm_eps); LLAMA_LOG_INFO("%s: f_norm_rms_eps = %.1e\n", __func__, hparams.f_norm_rms_eps); LLAMA_LOG_INFO("%s: f_clamp_kqv = %.1e\n", __func__, hparams.f_clamp_kqv); @@ -1725,7 +1727,7 @@ void llama_model::print_info() const { LLAMA_LOG_INFO("%s: f_logit_scale = %.1e\n", __func__, hparams.f_logit_scale); LLAMA_LOG_INFO("%s: f_attn_scale = %.1e\n", __func__, hparams.f_attention_scale); LLAMA_LOG_INFO("%s: f_attn_value_scale = %.4f\n", __func__, hparams.f_attn_value_scale); - LLAMA_LOG_INFO("%s: n_ff = %s\n", __func__, print_f([&](uint32_t il) { return hparams.n_ff(il); }, hparams.n_layer).c_str()); + LLAMA_LOG_INFO("%s: n_ff = %s\n", __func__, print_f([&](uint32_t il) { return hparams.n_ff(il); }, hparams.n_layer()).c_str()); LLAMA_LOG_INFO("%s: n_expert = %u\n", __func__, hparams.n_expert); LLAMA_LOG_INFO("%s: n_expert_used = %u\n", __func__, hparams.n_expert_used); LLAMA_LOG_INFO("%s: n_expert_groups = %d\n", __func__, hparams.n_expert_groups); @@ -1852,7 +1854,7 @@ void llama_model::print_info() const { LLAMA_LOG_INFO("%s: expert_weights_scale = %.1f\n", __func__, hparams.expert_weights_scale); LLAMA_LOG_INFO("%s: expert_weights_norm = %d\n", __func__, hparams.expert_weights_norm); LLAMA_LOG_INFO("%s: expert_gating_func = %s\n", __func__, llama_expert_gating_func_name((llama_expert_gating_func_type) hparams.expert_gating_func)); - LLAMA_LOG_INFO("%s: nextn_predict_layers = %d\n", __func__, hparams.nextn_predict_layers); + LLAMA_LOG_INFO("%s: n_layer_nextn = %d\n", __func__, hparams.n_layer_nextn); } if (arch == LLM_ARCH_SMALLTHINKER || arch == LLM_ARCH_LFM2MOE) { @@ -2034,22 +2036,21 @@ llama_memory_i * llama_model::create_memory(const llama_memory_params & params, llama_memory_hybrid::layer_filter_cb filter_attn = nullptr; llama_memory_hybrid::layer_filter_cb filter_recr = nullptr; if (arch == LLM_ARCH_FALCON_H1) { - filter_attn = [&](int32_t) { return true; }; - filter_recr = [&](int32_t) { return true; }; + filter_attn = [&](uint32_t) { return true; }; + filter_recr = [&](uint32_t) { return true; }; } else if (arch == LLM_ARCH_NEMOTRON_H || arch == LLM_ARCH_NEMOTRON_H_MOE) { - filter_attn = [&](int32_t il) { + filter_attn = [&](uint32_t il) { return !hparams.is_recr(il) && hparams.n_ff(il) == 0; }; - filter_recr = [&](int32_t il) { + filter_recr = [&](uint32_t il) { return hparams.is_recr(il) && hparams.n_ff(il) == 0; }; } else if (arch == LLM_ARCH_QWEN35 || arch == LLM_ARCH_QWEN35MOE) { - const uint32_t n_main = hparams.n_layer - hparams.nextn_predict_layers; - filter_attn = [&, n_main](int32_t il) { - return (uint32_t)il < n_main && !hparams.is_recr(il); + filter_attn = [&](uint32_t il) { + return il < hparams.n_layer() && !hparams.is_recr(il); }; - filter_recr = [&, n_main](int32_t il) { - return (uint32_t)il < n_main && hparams.is_recr(il); + filter_recr = [&](uint32_t il) { + return il < hparams.n_layer() && hparams.is_recr(il); }; } @@ -2098,9 +2099,11 @@ llama_memory_i * llama_model::create_memory(const llama_memory_params & params, llama_kv_cache::layer_filter_cb filter = nullptr; if (arch == LLM_ARCH_GEMMA3N || arch == LLM_ARCH_GEMMA4) { - reuse = [&](int32_t il) { - if (il >= (int32_t) hparams.n_layer_kv_from_start) { - return (int32_t) hparams.n_layer_kv_from_start - (hparams.is_swa(il) ? 2 : 1); + reuse = [&](uint32_t il) { + GGML_ASSERT(hparams.n_layer_kv_from_start >= 2); + + if (il >= (uint32_t)hparams.n_layer_kv_from_start) { + return hparams.n_layer_kv_from_start - (hparams.is_swa(il) ? 2 : 1); } return -1; @@ -2108,16 +2111,14 @@ llama_memory_i * llama_model::create_memory(const llama_memory_params & params, } if (mtp_on_hybrid_qwen35) { - const uint32_t n_main = hparams.n_layer - hparams.nextn_predict_layers; - filter = [n_main](int32_t il) { return (uint32_t)il >= n_main; }; + filter = [&](uint32_t il) { return il >= hparams.n_layer(); }; } - if (arch == LLM_ARCH_STEP35 && hparams.nextn_predict_layers > 0) { - const uint32_t n_main = hparams.n_layer - hparams.nextn_predict_layers; + if (arch == LLM_ARCH_STEP35 && hparams.n_layer_nextn > 0) { if (params.ctx_type == LLAMA_CONTEXT_TYPE_MTP) { - filter = [n_main](int32_t il) { return (uint32_t)il >= n_main; }; + filter = [&](uint32_t il) { return il >= hparams.n_layer(); }; } else { - filter = [n_main](int32_t il) { return (uint32_t)il < n_main; }; + filter = [&](uint32_t il) { return il < hparams.n_layer(); }; } } @@ -2242,7 +2243,7 @@ int32_t llama_model_n_embd_out(const llama_model * model) { } int32_t llama_model_n_layer(const llama_model * model) { - return model->hparams.n_layer; + return model->hparams.n_layer(); } int32_t llama_model_n_head(const llama_model * model) { @@ -2387,6 +2388,7 @@ llama_rope_type llama_model_rope_type(const llama_model * model) { case LLM_ARCH_GEMMA3: case LLM_ARCH_GEMMA3N: case LLM_ARCH_GEMMA4: + case LLM_ARCH_GEMMA4_ASSISTANT: case LLM_ARCH_GEMMA_EMBEDDING: case LLM_ARCH_STARCODER2: case LLM_ARCH_OPENELM: diff --git a/src/llama-model.h b/src/llama-model.h index a561374ed956..a3c068b84d45 100644 --- a/src/llama-model.h +++ b/src/llama-model.h @@ -548,6 +548,10 @@ struct llama_model { struct ggml_tensor * output_s = nullptr; struct ggml_tensor * output_in_s = nullptr; + // NextN/MTP model-level projections + struct ggml_tensor * nextn_pre_proj = nullptr; + struct ggml_tensor * nextn_post_proj = nullptr; + // classifier struct ggml_tensor * cls = nullptr; struct ggml_tensor * cls_b = nullptr; @@ -700,7 +704,8 @@ const char * llm_type_name(llm_type type); // convenience macro for loading local variables for load_tensors() in llama_model_base // note: cast to int64_t since we will use these for the tensor dimensions #define LLAMA_LOAD_LOCALS \ - const int n_layer = hparams.n_layer; GGML_UNUSED(n_layer); \ + const int n_layer = hparams.n_layer(); GGML_UNUSED(n_layer); \ + const int n_layer_all = hparams.n_layer_all; GGML_UNUSED(n_layer_all); \ const int64_t n_head = hparams.n_head(); GGML_UNUSED(n_head); \ const int64_t n_head_kv = hparams.n_head_kv(); GGML_UNUSED(n_head_kv); \ const int64_t n_embd = hparams.n_embd; GGML_UNUSED(n_embd); \ diff --git a/src/llama-quant.cpp b/src/llama-quant.cpp index 43e05c3d56fe..cf92ce4bb8b7 100644 --- a/src/llama-quant.cpp +++ b/src/llama-quant.cpp @@ -847,7 +847,7 @@ static void init_quantize_state_counters(quantize_state_impl & qs, std::vectorhparams.n_embd = desc->n_embd; model->hparams.n_embd_head_k_full = desc->n_embd_head_k; model->hparams.n_embd_head_v_full = desc->n_embd_head_v; - model->hparams.n_layer = desc->n_layer; + model->hparams.n_layer_all = desc->n_layer; model->hparams.n_expert = desc->n_expert; for (uint32_t i = 0; i < desc->n_layer; i++) { diff --git a/src/models/afmoe.cpp b/src/models/afmoe.cpp index a7c77ee5d28b..063b214256e7 100644 --- a/src/models/afmoe.cpp +++ b/src/models/afmoe.cpp @@ -30,7 +30,7 @@ void llama_model_afmoe::load_arch_hparams(llama_model_loader & ml) { hparams.expert_gating_func = LLAMA_EXPERT_GATING_FUNC_TYPE_SIGMOID; } - switch (hparams.n_layer) { + switch (hparams.n_layer()) { case 56: type = LLM_TYPE_6B; break; case 32: type = LLM_TYPE_26B; break; default: type = LLM_TYPE_UNKNOWN; diff --git a/src/models/apertus.cpp b/src/models/apertus.cpp index bec7136521c6..6dfb8905fbe5 100644 --- a/src/models/apertus.cpp +++ b/src/models/apertus.cpp @@ -2,12 +2,13 @@ void llama_model_apertus::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps); - ml.get_key_or_arr(LLM_KV_XIELU_ALPHA_N, hparams.xielu_alpha_n, hparams.n_layer); - ml.get_key_or_arr(LLM_KV_XIELU_ALPHA_P, hparams.xielu_alpha_p, hparams.n_layer); - ml.get_key_or_arr(LLM_KV_XIELU_BETA, hparams.xielu_beta, hparams.n_layer); - ml.get_key_or_arr(LLM_KV_XIELU_EPS, hparams.xielu_eps, hparams.n_layer); - switch (hparams.n_layer) { + ml.get_key_or_arr(LLM_KV_XIELU_ALPHA_N, hparams.xielu_alpha_n, hparams.n_layer()); + ml.get_key_or_arr(LLM_KV_XIELU_ALPHA_P, hparams.xielu_alpha_p, hparams.n_layer()); + ml.get_key_or_arr(LLM_KV_XIELU_BETA, hparams.xielu_beta, hparams.n_layer()); + ml.get_key_or_arr(LLM_KV_XIELU_EPS, hparams.xielu_eps, hparams.n_layer()); + + switch (hparams.n_layer()) { case 32: type = LLM_TYPE_8B; break; default: type = LLM_TYPE_UNKNOWN; } diff --git a/src/models/arcee.cpp b/src/models/arcee.cpp index d086c4717ff1..9536e7c5d429 100644 --- a/src/models/arcee.cpp +++ b/src/models/arcee.cpp @@ -4,7 +4,7 @@ void llama_model_arcee::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps); // Arcee uses the same structure as Llama - switch (hparams.n_layer) { + switch (hparams.n_layer()) { case 36: type = LLM_TYPE_4B; break; default: type = LLM_TYPE_UNKNOWN; } diff --git a/src/models/arctic.cpp b/src/models/arctic.cpp index 27deadffeb75..09ee0f752f0e 100644 --- a/src/models/arctic.cpp +++ b/src/models/arctic.cpp @@ -4,7 +4,7 @@ void llama_model_arctic::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps); if (hparams.n_expert == 128) { - switch (hparams.n_layer) { + switch (hparams.n_layer()) { case 35: type = LLM_TYPE_10B_128x3_66B; break; default: type = LLM_TYPE_UNKNOWN; } diff --git a/src/models/arwkv7.cpp b/src/models/arwkv7.cpp index 9bd04127b25a..b38b2064785b 100644 --- a/src/models/arwkv7.cpp +++ b/src/models/arwkv7.cpp @@ -10,7 +10,7 @@ void llama_model_arwkv7::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_ATTENTION_GATE_LORA_RANK, hparams.n_lora_gate, false); ml.get_key(LLM_KV_TOKEN_SHIFT_COUNT, hparams.token_shift_count, false); - switch (hparams.n_layer) { + switch (hparams.n_layer()) { case 12: switch (hparams.n_embd) { case 768: type = LLM_TYPE_190M; break; diff --git a/src/models/baichuan.cpp b/src/models/baichuan.cpp index 4d26081cd5d4..585f36141741 100644 --- a/src/models/baichuan.cpp +++ b/src/models/baichuan.cpp @@ -2,7 +2,7 @@ void llama_model_baichuan::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps); - switch (hparams.n_layer) { + switch (hparams.n_layer()) { case 32: type = LLM_TYPE_7B; break; case 40: type = LLM_TYPE_13B; break; default: type = LLM_TYPE_UNKNOWN; diff --git a/src/models/bailingmoe.cpp b/src/models/bailingmoe.cpp index fe1ae10864b8..7faf73c835b6 100644 --- a/src/models/bailingmoe.cpp +++ b/src/models/bailingmoe.cpp @@ -8,7 +8,7 @@ void llama_model_bailingmoe::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_EXPERT_WEIGHTS_SCALE, hparams.expert_weights_scale, false); ml.get_key(LLM_KV_EXPERT_WEIGHTS_NORM, hparams.expert_weights_norm, false); - switch (hparams.n_layer) { + switch (hparams.n_layer()) { case 28: type = LLM_TYPE_16B; break; case 88: type = LLM_TYPE_290B; break; default: type = LLM_TYPE_UNKNOWN; diff --git a/src/models/bailingmoe2.cpp b/src/models/bailingmoe2.cpp index 2f0d44a62596..5000e9c6db89 100644 --- a/src/models/bailingmoe2.cpp +++ b/src/models/bailingmoe2.cpp @@ -9,17 +9,13 @@ void llama_model_bailingmoe2::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_EXPERT_WEIGHTS_SCALE, hparams.expert_weights_scale, false); ml.get_key(LLM_KV_EXPERT_WEIGHTS_NORM, hparams.expert_weights_norm, false); ml.get_key(LLM_KV_EXPERT_GATING_FUNC, hparams.expert_gating_func); - ml.get_key(LLM_KV_NEXTN_PREDICT_LAYERS, hparams.nextn_predict_layers, false); - GGML_ASSERT(hparams.nextn_predict_layers < hparams.n_layer && "nextn_predict_layers must be < n_layer"); + ml.get_key(LLM_KV_NEXTN_PREDICT_LAYERS, hparams.n_layer_nextn, false); - // TODO: when MTP is implemented, this should probably be updated if needed - hparams.n_layer_kv_from_start = hparams.n_layer - hparams.nextn_predict_layers; + GGML_ASSERT(hparams.n_layer_nextn < hparams.n_layer_all && "n_layer_nextn must be < n_layer_impl"); - switch (hparams.n_layer) { + switch (hparams.n_layer()) { case 20: type = LLM_TYPE_16B_A1B; break; - case 21: type = LLM_TYPE_16B_A1B; break; case 32: type = LLM_TYPE_100B_A6B; break; - case 33: type = LLM_TYPE_100B_A6B; break; default: type = LLM_TYPE_UNKNOWN; } } @@ -39,9 +35,9 @@ void llama_model_bailingmoe2::load_arch_tensors(llama_model_loader &) { GGML_ASSERT(n_expert > 0 && "n_expert must be > 0 for bailingmoe2"); GGML_ASSERT(n_expert_used > 0 && "n_expert_used must be > 0 for bailingmoe2"); - for (int i = 0; i < n_layer; ++i) { + for (int i = 0; i < n_layer_all; ++i) { int flags = 0; - if (hparams.nextn_predict_layers > 0 && static_cast(i) >= n_layer - hparams.nextn_predict_layers) { + if (i >= n_layer) { // skip all tensors in the NextN layers flags |= TENSOR_SKIP; } @@ -78,7 +74,7 @@ void llama_model_bailingmoe2::load_arch_tensors(llama_model_loader &) { } // NextN/MTP tensors (preserved but unused) - conditionally load for last nextn_predict_layers - if (hparams.nextn_predict_layers > 0 && static_cast(i) >= n_layer - hparams.nextn_predict_layers) { + if (i >= n_layer) { layer.nextn.eh_proj = create_tensor(tn(LLM_TENSOR_NEXTN_EH_PROJ, "weight", i), { 2 * n_embd, n_embd }, flags); layer.nextn.embed_tokens = create_tensor(tn(LLM_TENSOR_NEXTN_EMBED_TOKENS, "weight", i), { n_embd, n_vocab }, TENSOR_NOT_REQUIRED | flags); layer.nextn.enorm = create_tensor(tn(LLM_TENSOR_NEXTN_ENORM, "weight", i), { n_embd }, flags); @@ -112,8 +108,7 @@ llama_model_bailingmoe2::graph::graph(const llama_model & model, const llm_graph ggml_tensor * inp_out_ids = build_inp_out_ids(); - const int n_transformer_layers = n_layer - hparams.nextn_predict_layers; - for (int il = 0; il < n_transformer_layers; ++il) { + for (int il = 0; il < n_layer; ++il) { ggml_tensor * inpSA = inpL; // norm @@ -146,7 +141,7 @@ llama_model_bailingmoe2::graph::graph(const llama_model & model, const llm_graph Qcur, Kcur, Vcur, nullptr, nullptr, nullptr, 1.0f / sqrtf(float(n_embd_head)), il); } - if (il == n_transformer_layers - 1 && inp_out_ids) { + if (il == n_layer - 1 && inp_out_ids) { cur = ggml_get_rows(ctx0, cur, inp_out_ids); inpSA = ggml_get_rows(ctx0, inpSA, inp_out_ids); } diff --git a/src/models/bert.cpp b/src/models/bert.cpp index 3c28f419ccf2..53ce29f23cae 100644 --- a/src/models/bert.cpp +++ b/src/models/bert.cpp @@ -1,9 +1,9 @@ #include "models.h" void llama_model_bert::load_arch_hparams(llama_model_loader & ml) { - ml.get_key(LLM_KV_ATTENTION_LAYERNORM_EPS, hparams.f_norm_eps); + ml.get_key(LLM_KV_ATTENTION_LAYERNORM_EPS, hparams.f_norm_eps); - switch (hparams.n_layer) { + switch (hparams.n_layer()) { case 3: type = LLM_TYPE_17M; break; // bge-micro case 6: diff --git a/src/models/bitnet.cpp b/src/models/bitnet.cpp index 7e8125deec40..c83302745806 100644 --- a/src/models/bitnet.cpp +++ b/src/models/bitnet.cpp @@ -3,7 +3,7 @@ void llama_model_bitnet::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps); - switch (hparams.n_layer) { + switch (hparams.n_layer()) { case 26: type = LLM_TYPE_3B; break; default: type = LLM_TYPE_UNKNOWN; } diff --git a/src/models/bloom.cpp b/src/models/bloom.cpp index 30b0f3d07d06..609d2ddf998b 100644 --- a/src/models/bloom.cpp +++ b/src/models/bloom.cpp @@ -3,7 +3,7 @@ void llama_model_bloom::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_ATTENTION_LAYERNORM_EPS, hparams.f_norm_eps); - switch (hparams.n_layer) { + switch (hparams.n_layer()) { case 24: type = LLM_TYPE_1B; break; case 30: switch (hparams.n_embd) { diff --git a/src/models/chameleon.cpp b/src/models/chameleon.cpp index 4bceaefd63b3..4f45acecf848 100644 --- a/src/models/chameleon.cpp +++ b/src/models/chameleon.cpp @@ -6,7 +6,7 @@ void llama_model_chameleon::load_arch_hparams(llama_model_loader & ml) { hparams.f_norm_eps = 1e-5; // eps for qk-norm, torch default ml.get_key(LLM_KV_SWIN_NORM, hparams.swin_norm, false); - switch (hparams.n_layer) { + switch (hparams.n_layer()) { case 32: type = LLM_TYPE_7B; break; case 48: type = LLM_TYPE_34B; break; default: type = LLM_TYPE_UNKNOWN; diff --git a/src/models/chatglm.cpp b/src/models/chatglm.cpp index 6766fa71c159..7ae5b938fde3 100644 --- a/src/models/chatglm.cpp +++ b/src/models/chatglm.cpp @@ -2,7 +2,8 @@ void llama_model_chatglm::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps); - switch (hparams.n_layer) { + + switch (hparams.n_layer()) { case 28: { if (hparams.n_head(0) == 16) { type = LLM_TYPE_1_5B; diff --git a/src/models/codeshell.cpp b/src/models/codeshell.cpp index 274dd3342a7b..de53bb981847 100644 --- a/src/models/codeshell.cpp +++ b/src/models/codeshell.cpp @@ -2,7 +2,8 @@ void llama_model_codeshell::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_ATTENTION_LAYERNORM_EPS, hparams.f_norm_eps); - switch (hparams.n_layer) { + + switch (hparams.n_layer()) { case 42: type = LLM_TYPE_7B; break; default: type = LLM_TYPE_UNKNOWN; } diff --git a/src/models/cogvlm.cpp b/src/models/cogvlm.cpp index 2e231bb3f935..750f57a394e3 100644 --- a/src/models/cogvlm.cpp +++ b/src/models/cogvlm.cpp @@ -2,7 +2,8 @@ void llama_model_cogvlm::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps); - switch (hparams.n_layer) { + + switch (hparams.n_layer()) { case 32: type = LLM_TYPE_13B; break; default: type = LLM_TYPE_UNKNOWN; } diff --git a/src/models/cohere2.cpp b/src/models/cohere2.cpp index a514cf88fc63..61a5945a1948 100644 --- a/src/models/cohere2.cpp +++ b/src/models/cohere2.cpp @@ -5,6 +5,7 @@ void llama_model_cohere2::load_arch_hparams(llama_model_loader & ml) { uint32_t swa_period = 4; ml.get_key_or_arr(LLM_KV_ATTENTION_SLIDING_WINDOW_PATTERN, swa_period, false); hparams.set_swa_pattern(swa_period); + hparams.rope_freq_base_train_swa = hparams.rope_freq_base_train; hparams.rope_freq_scale_train_swa = hparams.rope_freq_scale_train; @@ -12,7 +13,8 @@ void llama_model_cohere2::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_ATTENTION_SLIDING_WINDOW, hparams.n_swa); ml.get_key(LLM_KV_LOGIT_SCALE, hparams.f_logit_scale); ml.get_key(LLM_KV_ATTENTION_LAYERNORM_EPS, hparams.f_norm_eps); - switch (hparams.n_layer) { + + switch (hparams.n_layer()) { case 32: type = LLM_TYPE_8B; break; default: type = LLM_TYPE_UNKNOWN; } diff --git a/src/models/command-r.cpp b/src/models/command-r.cpp index adf7fcaa20f8..94a46188bb89 100644 --- a/src/models/command-r.cpp +++ b/src/models/command-r.cpp @@ -3,7 +3,8 @@ void llama_model_command_r::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_LOGIT_SCALE, hparams.f_logit_scale, false); ml.get_key(LLM_KV_ATTENTION_LAYERNORM_EPS, hparams.f_norm_eps); - switch (hparams.n_layer) { + + switch (hparams.n_layer()) { case 40: type = LLM_TYPE_35B; break; default: type = LLM_TYPE_UNKNOWN; } diff --git a/src/models/dbrx.cpp b/src/models/dbrx.cpp index af71c7753658..4f5ac4d06a45 100644 --- a/src/models/dbrx.cpp +++ b/src/models/dbrx.cpp @@ -1,14 +1,14 @@ #include "models.h" void llama_model_dbrx::load_arch_hparams(llama_model_loader & ml) { -ml.get_key(LLM_KV_ATTENTION_LAYERNORM_EPS, hparams.f_norm_eps); -ml.get_key(LLM_KV_ATTENTION_CLAMP_KQV, hparams.f_clamp_kqv); + ml.get_key(LLM_KV_ATTENTION_LAYERNORM_EPS, hparams.f_norm_eps); + ml.get_key(LLM_KV_ATTENTION_CLAMP_KQV, hparams.f_clamp_kqv); -switch (hparams.n_layer) { - case 40: type = LLM_TYPE_16x12B; break; - default: type = LLM_TYPE_UNKNOWN; + switch (hparams.n_layer()) { + case 40: type = LLM_TYPE_16x12B; break; + default: type = LLM_TYPE_UNKNOWN; + } } - } void llama_model_dbrx::load_arch_tensors(llama_model_loader &) { LLAMA_LOAD_LOCALS; diff --git a/src/models/deci.cpp b/src/models/deci.cpp index 567e35352761..cdfcf29e02f5 100644 --- a/src/models/deci.cpp +++ b/src/models/deci.cpp @@ -2,7 +2,8 @@ void llama_model_deci::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps); - switch (hparams.n_layer) { + + switch (hparams.n_layer()) { case 32: type = LLM_TYPE_7B; break; case 80: type = LLM_TYPE_70B; break; case 162: type = LLM_TYPE_405B; break; diff --git a/src/models/deepseek2.cpp b/src/models/deepseek2.cpp index 1fe54adc13e2..a9e8bc514036 100644 --- a/src/models/deepseek2.cpp +++ b/src/models/deepseek2.cpp @@ -5,7 +5,7 @@ void llama_model_deepseek2::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_VOCAB_SIZE, n_vocab, false) || ml.get_arr_n(LLM_KV_TOKENIZER_LIST, n_vocab, false); // lite variants include DeepSeek-V2-Lite, GigaChat3-10B-A1.8B, Kanana-2-30B-A3B - const bool is_lite = (hparams.n_layer == 27 || hparams.n_layer == 26 || (hparams.n_layer == 48 && n_vocab == 128256)); + const bool is_lite = (hparams.n_layer() == 27 || hparams.n_layer() == 26 || (hparams.n_layer() == 48 && n_vocab == 128256)); ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps); ml.get_key(LLM_KV_LEADING_DENSE_BLOCK_COUNT, hparams.n_layer_dense_lead, false); @@ -23,7 +23,7 @@ void llama_model_deepseek2::load_arch_hparams(llama_model_loader & ml) { if (hparams.expert_gating_func == LLAMA_EXPERT_GATING_FUNC_TYPE_NONE) { // for compatibility with existing DeepSeek V2 and V2.5 GGUFs // that have no expert_gating_func model parameter set - if ((hparams.n_layer == 47 || hparams.n_layer == 48) && n_vocab == 154880) { + if ((hparams.n_layer() == 47 || hparams.n_layer() == 48) && n_vocab == 154880) { // GLM 4.7 Lite hparams.expert_gating_func = LLAMA_EXPERT_GATING_FUNC_TYPE_SIGMOID; } else { @@ -43,7 +43,7 @@ void llama_model_deepseek2::load_arch_hparams(llama_model_loader & ml) { hparams.f_attn_temp_offset = 0.0f; - switch (hparams.n_layer) { + switch (hparams.n_layer()) { case 27: type = LLM_TYPE_16B; break; case 47: type = LLM_TYPE_30B_A3B; break; case 60: type = LLM_TYPE_236B; break; @@ -191,8 +191,7 @@ llama_model_deepseek2::graph::graph(const llama_model & model, const llm_graph_p ggml_tensor * inp_out_ids = build_inp_out_ids(); - int effective_n_layers = hparams.n_layer - hparams.nextn_predict_layers; - for (int il = 0; il < effective_n_layers; ++il) { + for (int il = 0; il < n_layer; ++il) { ggml_tensor * inpSA = inpL; // norm @@ -366,7 +365,7 @@ llama_model_deepseek2::graph::graph(const llama_model & model, const llm_graph_p Qcur, Kcur, Vcur, nullptr, nullptr, nullptr, kq_scale, il); } } - if (il == effective_n_layers - 1 && inp_out_ids) { + if (il == n_layer - 1 && inp_out_ids) { cur = ggml_get_rows(ctx0, cur, inp_out_ids); inpSA = ggml_get_rows(ctx0, inpSA, inp_out_ids); } diff --git a/src/models/deepseek2ocr.cpp b/src/models/deepseek2ocr.cpp index f9e4c98785c1..65d31c31b93e 100644 --- a/src/models/deepseek2ocr.cpp +++ b/src/models/deepseek2ocr.cpp @@ -14,7 +14,7 @@ void llama_model_deepseek2ocr::load_arch_hparams(llama_model_loader & ml) { hparams.expert_gating_func = LLAMA_EXPERT_GATING_FUNC_TYPE_SOFTMAX; } - switch (hparams.n_layer) { + switch (hparams.n_layer()) { case 12: type = LLM_TYPE_3B; break; default: type = LLM_TYPE_UNKNOWN; } diff --git a/src/models/deepseek32.cpp b/src/models/deepseek32.cpp index c92ab60d1663..9a20e2ce9077 100644 --- a/src/models/deepseek32.cpp +++ b/src/models/deepseek32.cpp @@ -31,7 +31,7 @@ void llama_model_deepseek32::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_ATTENTION_INDEXER_TOP_K, hparams.indexer_top_k); // Expert gating function - ml.get_key(LLM_KV_EXPERT_GATING_FUNC, hparams.expert_gating_func); + ml.get_key(LLM_KV_EXPERT_GATING_FUNC, hparams.expert_gating_func); if (ml.get_key(LLM_KV_ROPE_SCALING_YARN_LOG_MUL, hparams.rope_yarn_log_mul, 0.0f)) { // [TAG_DEEPSEEK2_YARN_LOG_MUL_FIX] @@ -40,13 +40,10 @@ void llama_model_deepseek32::load_arch_hparams(llama_model_loader & ml) { } // NextN/MTP parameters - ml.get_key(LLM_KV_NEXTN_PREDICT_LAYERS, hparams.nextn_predict_layers, false); - GGML_ASSERT(hparams.nextn_predict_layers < hparams.n_layer && "nextn_predict_layers must be < n_layer"); + ml.get_key(LLM_KV_NEXTN_PREDICT_LAYERS, hparams.n_layer_nextn, false); + GGML_ASSERT(hparams.n_layer_nextn < hparams.n_layer_all && "n_layer_nextn must be < n_layer"); - // TODO: when MTP is implemented, this should probably be updated if needed - hparams.n_layer_kv_from_start = hparams.n_layer - hparams.nextn_predict_layers; - - switch (hparams.n_layer) { + switch (hparams.n_layer()) { case 62: type = LLM_TYPE_685B_A37B; break; default: type = LLM_TYPE_UNKNOWN; } @@ -82,9 +79,9 @@ void llama_model_deepseek32::load_arch_tensors(llama_model_loader &) { output = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}, TENSOR_DUPLICATED); } - for (int i = 0; i < n_layer; ++i) { + for (int i = 0; i < n_layer_all; ++i) { int flags = 0; - if (hparams.nextn_predict_layers > 0 && static_cast(i) >= n_layer - hparams.nextn_predict_layers) { + if (i >= n_layer) { // skip all tensors in the NextN layers // TODO @ngxson : TENSOR_NOT_REQUIRED was a hack, need to remove it later flags |= TENSOR_SKIP | TENSOR_NOT_REQUIRED; @@ -142,7 +139,7 @@ void llama_model_deepseek32::load_arch_tensors(llama_model_loader &) { } // NextN/MTP tensors (preserved but unused) - conditionally load for last nextn_predict_layers - if (hparams.nextn_predict_layers > 0 && static_cast(i) >= n_layer - hparams.nextn_predict_layers) { + if (i >= n_layer) { layer.nextn.eh_proj = create_tensor(tn(LLM_TENSOR_NEXTN_EH_PROJ, "weight", i), { 2 * n_embd, n_embd }, flags); layer.nextn.enorm = create_tensor(tn(LLM_TENSOR_NEXTN_ENORM, "weight", i), { n_embd }, flags); layer.nextn.hnorm = create_tensor(tn(LLM_TENSOR_NEXTN_HNORM, "weight", i), { n_embd }, flags); @@ -205,8 +202,7 @@ llama_model_deepseek32::graph::graph(const llama_model & model, const llm_graph_ ggml_tensor * inp_out_ids = build_inp_out_ids(); - int effective_n_layers = hparams.n_layer - hparams.nextn_predict_layers; - for (int il = 0; il < effective_n_layers; ++il) { + for (int il = 0; il < n_layer; ++il) { ggml_tensor * inpSA = inpL; // norm @@ -427,7 +423,7 @@ llama_model_deepseek32::graph::graph(const llama_model & model, const llm_graph_ Qcur, Kcur, Vcur, nullptr, nullptr, model.layers[il].wv_b, top_k, kq_scale, il); } } - if (il == effective_n_layers - 1 && inp_out_ids) { + if (il == n_layer - 1 && inp_out_ids) { cur = ggml_get_rows(ctx0, cur, inp_out_ids); inpSA = ggml_get_rows(ctx0, inpSA, inp_out_ids); } diff --git a/src/models/dots1.cpp b/src/models/dots1.cpp index 435d27281c69..07d6ab1b7cdb 100644 --- a/src/models/dots1.cpp +++ b/src/models/dots1.cpp @@ -8,7 +8,8 @@ void llama_model_dots1::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_EXPERT_WEIGHTS_SCALE, hparams.expert_weights_scale, false); ml.get_key(LLM_KV_EXPERT_WEIGHTS_NORM, hparams.expert_weights_norm, false); ml.get_key(LLM_KV_EXPERT_GATING_FUNC, hparams.expert_gating_func, false); - switch (hparams.n_layer) { + + switch (hparams.n_layer()) { case 62: type = LLM_TYPE_142B; break; default: type = LLM_TYPE_UNKNOWN; } diff --git a/src/models/dream.cpp b/src/models/dream.cpp index 12ac6f1ce88f..abe737c335a4 100644 --- a/src/models/dream.cpp +++ b/src/models/dream.cpp @@ -2,8 +2,9 @@ void llama_model_dream::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps); + // Dream models are primarily 7B with 28 layers - switch (hparams.n_layer) { + switch (hparams.n_layer()) { case 28: type = LLM_TYPE_7B; break; diff --git a/src/models/ernie4-5.cpp b/src/models/ernie4-5.cpp index 9b39c605e350..895cf690bd2d 100644 --- a/src/models/ernie4-5.cpp +++ b/src/models/ernie4-5.cpp @@ -12,7 +12,7 @@ void llama_model_ernie4_5::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_LEADING_DENSE_BLOCK_COUNT, hparams.n_layer_dense_lead, false); } - switch (hparams.n_layer) { + switch (hparams.n_layer()) { case 18: type = LLM_TYPE_0_3B; break; case 28: type = LLM_TYPE_21B_A3B; break; case 54: type = LLM_TYPE_300B_A47B; break; diff --git a/src/models/eurobert.cpp b/src/models/eurobert.cpp index ddf13c3028f2..0948d7de656f 100644 --- a/src/models/eurobert.cpp +++ b/src/models/eurobert.cpp @@ -3,7 +3,7 @@ void llama_model_eurobert::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps); - if (hparams.n_layer == 12) { + if (hparams.n_layer() == 12) { type = LLM_TYPE_SMALL; // 0.2B } } diff --git a/src/models/exaone-moe.cpp b/src/models/exaone-moe.cpp index 76d91982fc53..5aed9379400c 100644 --- a/src/models/exaone-moe.cpp +++ b/src/models/exaone-moe.cpp @@ -20,13 +20,12 @@ void llama_model_exaone_moe::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_EXPERT_WEIGHTS_NORM, hparams.expert_weights_norm, false); ml.get_key(LLM_KV_LEADING_DENSE_BLOCK_COUNT, hparams.n_layer_dense_lead, false); - ml.get_key(LLM_KV_NEXTN_PREDICT_LAYERS, hparams.nextn_predict_layers, false); - GGML_ASSERT(hparams.nextn_predict_layers < hparams.n_layer && "nextn_predict_layers must be < n_layer"); + ml.get_key(LLM_KV_NEXTN_PREDICT_LAYERS, hparams.n_layer_nextn, false); + GGML_ASSERT(hparams.n_layer_nextn < hparams.n_layer_all && "n_layer_nextn must be < n_layer_impl"); - switch (hparams.n_layer) { + switch (hparams.n_layer()) { case 32: type = LLM_TYPE_30B_A3B; break; - case 48: - case 49: type = LLM_TYPE_235B_A22B; break; + case 48: type = LLM_TYPE_235B_A22B; break; default: type = LLM_TYPE_UNKNOWN; } } @@ -50,9 +49,9 @@ void llama_model_exaone_moe::load_arch_tensors(llama_model_loader &) { output = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}, TENSOR_DUPLICATED); } - for (int i = 0; i < n_layer; ++i) { + for (int i = 0; i < n_layer_all; ++i) { int flags = 0; - if (hparams.nextn_predict_layers > 0 && static_cast(i) >= n_layer - hparams.nextn_predict_layers) { + if (i >= n_layer) { // skip all tensors in the NextN layers flags |= TENSOR_SKIP; } @@ -70,7 +69,7 @@ void llama_model_exaone_moe::load_arch_tensors(llama_model_loader &) { layer.ffn_norm = create_tensor(tn(LLM_TENSOR_FFN_NORM, "weight", i), {n_embd}, flags); // dense layers for first n_layer_dense_lead layers or nextn_predict_layers layers at the end - if (i < (int) hparams.n_layer_dense_lead || (hparams.nextn_predict_layers > 0 && static_cast(i) >= n_layer - hparams.nextn_predict_layers)) { + if (i < (int) hparams.n_layer_dense_lead || (i >= n_layer)) { layer.ffn_gate = create_tensor(tn(LLM_TENSOR_FFN_GATE, "weight", i), {n_embd, n_ff}, flags); layer.ffn_down = create_tensor(tn(LLM_TENSOR_FFN_DOWN, "weight", i), {n_ff, n_embd}, flags); layer.ffn_up = create_tensor(tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff}, flags); @@ -95,7 +94,7 @@ void llama_model_exaone_moe::load_arch_tensors(llama_model_loader &) { } // NextN/MTP tensors (preserved but unused) - conditionally load for last nextn_predict_layers - if (hparams.nextn_predict_layers > 0 && static_cast(i) >= n_layer - hparams.nextn_predict_layers) { + if (i >= n_layer) { layer.nextn.eh_proj = create_tensor(tn(LLM_TENSOR_NEXTN_EH_PROJ, "weight", i), {2 * n_embd, n_embd}, flags); layer.nextn.enorm = create_tensor(tn(LLM_TENSOR_NEXTN_ENORM, "weight", i), {n_embd}, flags); layer.nextn.hnorm = create_tensor(tn(LLM_TENSOR_NEXTN_HNORM, "weight", i), {n_embd}, flags); @@ -130,8 +129,7 @@ llama_model_exaone_moe::graph::graph(const llama_model & model, const llm_graph_ ggml_tensor * inp_out_ids = build_inp_out_ids(); - const int n_transformer_layers = n_layer - hparams.nextn_predict_layers; - for (int il = 0; il < n_transformer_layers; ++il) { + for (int il = 0; il < n_layer; ++il) { ggml_tensor * inpSA = inpL; // use RoPE for SWA layers @@ -170,7 +168,7 @@ llama_model_exaone_moe::graph::graph(const llama_model & model, const llm_graph_ Qcur, Kcur, Vcur, nullptr, nullptr, nullptr, 1.0f / sqrtf(float(n_embd_head)), il); cb(cur, "attn_out", il); } - if (il == n_transformer_layers - 1 && inp_out_ids) { + if (il == n_layer - 1 && inp_out_ids) { cur = ggml_get_rows(ctx0, cur, inp_out_ids); inpSA = ggml_get_rows(ctx0, inpSA, inp_out_ids); } diff --git a/src/models/exaone.cpp b/src/models/exaone.cpp index c7e9960d7185..676fb37b5a63 100644 --- a/src/models/exaone.cpp +++ b/src/models/exaone.cpp @@ -3,7 +3,7 @@ void llama_model_exaone::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps); - switch (hparams.n_layer) { + switch (hparams.n_layer()) { case 32: type = LLM_TYPE_8B; break; default: type = LLM_TYPE_UNKNOWN; } diff --git a/src/models/exaone4.cpp b/src/models/exaone4.cpp index b5030eb05459..863268abcef2 100644 --- a/src/models/exaone4.cpp +++ b/src/models/exaone4.cpp @@ -1,7 +1,7 @@ #include "models.h" void llama_model_exaone4::load_arch_hparams(llama_model_loader & ml) { - if (hparams.n_layer == 64) { // 32B + if (hparams.n_layer() == 64) { // 32B hparams.swa_type = LLAMA_SWA_TYPE_STANDARD; hparams.n_swa = 4096; uint32_t swa_period = 4; @@ -15,11 +15,11 @@ void llama_model_exaone4::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_ATTENTION_SLIDING_WINDOW, hparams.n_swa, false); ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps); - ml.get_key(LLM_KV_NEXTN_PREDICT_LAYERS, hparams.nextn_predict_layers, false); - GGML_ASSERT(hparams.nextn_predict_layers < hparams.n_layer && "nextn_predict_layers must be < n_layer"); - hparams.n_layer_kv_from_start = hparams.n_layer - hparams.nextn_predict_layers; + ml.get_key(LLM_KV_NEXTN_PREDICT_LAYERS, hparams.n_layer_nextn, false); - switch (hparams.n_layer) { + GGML_ASSERT(hparams.n_layer_nextn < hparams.n_layer_all && "n_layer_nextn must be < n_layer"); + + switch (hparams.n_layer()) { case 30: type = LLM_TYPE_1_2B; break; case 64: type = LLM_TYPE_32B; break; default: type = LLM_TYPE_UNKNOWN; @@ -40,8 +40,8 @@ void llama_model_exaone4::load_arch_tensors(llama_model_loader &) { output = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}, TENSOR_DUPLICATED); } - for (int i = 0; i < n_layer; ++i) { - const bool is_nextn = hparams.nextn_predict_layers > 0 && static_cast(i) >= n_layer - hparams.nextn_predict_layers; + for (int i = 0; i < n_layer_all; ++i) { + const bool is_nextn = i >= n_layer; int flags = 0; if (is_nextn) { // NextN/MTP layers are preserved in GGUF but are not executed yet. @@ -109,11 +109,7 @@ llama_model_exaone4::graph::graph(const llama_model & model, const llm_gra } ggml_tensor * inp_out_ids = build_inp_out_ids(); - // MTP / NextN tail blocks are loaded for compatibility but not executed (same as exaone-moe). - const int n_layer_main = int(n_layer) - int(hparams.nextn_predict_layers); - GGML_ASSERT(n_layer_main > 0); - - for (int il = 0; il < n_layer_main; ++il) { + for (int il = 0; il < n_layer; ++il) { ggml_tensor * inpSA = inpL; // use RoPE for SWA layers or non-SWA models @@ -149,7 +145,7 @@ llama_model_exaone4::graph::graph(const llama_model & model, const llm_gra Qcur, Kcur, Vcur, nullptr, nullptr, nullptr, 1.0f / sqrtf(float(n_embd_head)), il); cb(cur, "attn_out", il); } - if (il == n_layer_main - 1 && inp_out_ids) { + if (il == n_layer - 1 && inp_out_ids) { cur = ggml_get_rows(ctx0, cur, inp_out_ids); inpSA = ggml_get_rows(ctx0, inpSA, inp_out_ids); } diff --git a/src/models/falcon-h1.cpp b/src/models/falcon-h1.cpp index c130ccdd49ee..d6ef2d519862 100644 --- a/src/models/falcon-h1.cpp +++ b/src/models/falcon-h1.cpp @@ -13,7 +13,7 @@ void llama_model_falcon_h1::load_arch_hparams(llama_model_loader & ml) { std::fill(hparams.is_recr_impl.begin(), hparams.is_recr_impl.end(), true); - switch (hparams.n_layer) { + switch (hparams.n_layer()) { case 36: type = LLM_TYPE_0_5B; break; case 24: diff --git a/src/models/falcon.cpp b/src/models/falcon.cpp index ad546ef2db56..b2ad90b32724 100644 --- a/src/models/falcon.cpp +++ b/src/models/falcon.cpp @@ -3,7 +3,7 @@ void llama_model_falcon::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_ATTENTION_LAYERNORM_EPS, hparams.f_norm_eps); - switch (hparams.n_layer) { + switch (hparams.n_layer()) { case 32: type = LLM_TYPE_7B; break; case 60: type = LLM_TYPE_40B; break; default: type = LLM_TYPE_UNKNOWN; diff --git a/src/models/gemma-embedding.cpp b/src/models/gemma-embedding.cpp index 4e07f5f2bdaf..80ed3b1a4605 100644 --- a/src/models/gemma-embedding.cpp +++ b/src/models/gemma-embedding.cpp @@ -21,7 +21,7 @@ void llama_model_gemma_embedding::load_arch_hparams(llama_model_loader & ml) { GGML_ASSERT((hparams.dense_2_feat_in == 0 || hparams.dense_2_feat_in == hparams.n_embd) && "dense_2_feat_in must be equal to n_embd"); GGML_ASSERT((hparams.dense_3_feat_out == 0 || hparams.dense_3_feat_out == hparams.n_embd) && "dense_3_feat_out must be equal to n_embd"); - switch (hparams.n_layer) { + switch (hparams.n_layer()) { case 24: type = LLM_TYPE_0_3B; break; default: type = LLM_TYPE_UNKNOWN; } diff --git a/src/models/gemma.cpp b/src/models/gemma.cpp index 1519682fdf62..651cd7e64de0 100644 --- a/src/models/gemma.cpp +++ b/src/models/gemma.cpp @@ -3,7 +3,7 @@ void llama_model_gemma::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps); - switch (hparams.n_layer) { + switch (hparams.n_layer()) { case 18: type = LLM_TYPE_2B; break; case 28: type = LLM_TYPE_7B; break; default: type = LLM_TYPE_UNKNOWN; diff --git a/src/models/gemma2.cpp b/src/models/gemma2.cpp index ae3f9ffb5301..2fbfb15a94a3 100644 --- a/src/models/gemma2.cpp +++ b/src/models/gemma2.cpp @@ -16,7 +16,7 @@ void llama_model_gemma2::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_ATTN_LOGIT_SOFTCAPPING, hparams.f_attn_logit_softcapping, false); ml.get_key(LLM_KV_FINAL_LOGIT_SOFTCAPPING, hparams.f_final_logit_softcapping, false); - switch (hparams.n_layer) { + switch (hparams.n_layer()) { case 26: type = LLM_TYPE_2B; break; case 42: type = LLM_TYPE_9B; break; case 46: type = LLM_TYPE_27B; break; diff --git a/src/models/gemma3.cpp b/src/models/gemma3.cpp index 63a2b380e71a..690194529e38 100644 --- a/src/models/gemma3.cpp +++ b/src/models/gemma3.cpp @@ -17,7 +17,7 @@ void llama_model_gemma3::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_FINAL_LOGIT_SOFTCAPPING, hparams.f_final_logit_softcapping, false); ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps); - switch (hparams.n_layer) { + switch (hparams.n_layer()) { case 18: type = LLM_TYPE_270M; break; case 26: type = LLM_TYPE_1B; break; case 32: type = LLM_TYPE_8B; break; // Rnj-1 diff --git a/src/models/gemma3n.cpp b/src/models/gemma3n.cpp index 6ec3a006081f..83eb8250aa94 100644 --- a/src/models/gemma3n.cpp +++ b/src/models/gemma3n.cpp @@ -6,14 +6,14 @@ void llama_model_gemma3n::load_arch_hparams(llama_model_loader & ml) { hparams.swa_type = LLAMA_SWA_TYPE_STANDARD; hparams.set_swa_pattern(swa_period); - hparams.n_layer_kv_from_start = 20; - hparams.f_attention_scale = 1.0f; + hparams.n_layer_kv_from_start = 20; + hparams.f_attention_scale = 1.0f; ml.get_key(LLM_KV_ROPE_FREQ_BASE_SWA, hparams.rope_freq_base_train_swa, false); ml.get_key(LLM_KV_ATTENTION_SLIDING_WINDOW, hparams.n_swa); ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps); - switch (hparams.n_layer) { + switch (hparams.n_layer()) { case 30: type = LLM_TYPE_E2B; break; case 35: type = LLM_TYPE_E4B; break; default: type = LLM_TYPE_UNKNOWN; diff --git a/src/models/gemma4-assistant.cpp b/src/models/gemma4-assistant.cpp new file mode 100644 index 000000000000..8c274e0cbd3d --- /dev/null +++ b/src/models/gemma4-assistant.cpp @@ -0,0 +1,209 @@ +#include "models.h" + +void llama_model_gemma4_assistant::load_arch_hparams(llama_model_loader & ml) { + hparams.swa_type = LLAMA_SWA_TYPE_STANDARD; + ml.get_key_or_arr(LLM_KV_ATTENTION_SLIDING_WINDOW_PATTERN, hparams.is_swa_impl, hparams.n_layer()); + + uint32_t n_kv_shared_layers = 0; + ml.get_key(LLM_KV_ATTENTION_SHARED_KV_LAYERS, n_kv_shared_layers, false); + + hparams.f_attention_scale = 1.0f; + + ml.get_key(LLM_KV_ROPE_FREQ_BASE_SWA, hparams.rope_freq_base_train_swa, false); + ml.get_key(LLM_KV_ATTENTION_SLIDING_WINDOW, hparams.n_swa); + ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps); + ml.get_key(LLM_KV_ATTENTION_KEY_LENGTH_SWA, hparams.n_embd_head_k_swa); + ml.get_key(LLM_KV_ATTENTION_VALUE_LENGTH_SWA, hparams.n_embd_head_v_swa); + + if (hparams.n_layer() == 4) { + type = LLM_TYPE_31B; + } +} + +void llama_model_gemma4_assistant::load_arch_tensors(llama_model_loader &) { + LLAMA_LOAD_LOCALS; + + if (n_embd_head_k != n_embd_head_v) { + throw std::runtime_error("Gemma 4 assistant requires n_embd_head_k == n_embd_head_v"); + } + if (hparams.n_embd_head_k_swa != hparams.n_embd_head_v_swa) { + throw std::runtime_error("Gemma 4 assistant requires n_embd_head_k_swa == n_embd_head_v_swa"); + } + if (hparams.n_embd_out() == n_embd) { + throw std::runtime_error("Gemma 4 assistant requires embedding_length_out to carry the target hidden size"); + } + + tok_embd = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD, "weight"), { n_embd, n_vocab }, 0); + output = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD, "weight"), { n_embd, n_vocab }, TENSOR_DUPLICATED); + + output_norm = create_tensor(tn(LLM_TENSOR_OUTPUT_NORM, "weight"), { n_embd }, 0); + + const int64_t n_embd_backbone = hparams.n_embd_out(); + nextn_post_proj = create_tensor(tn(LLM_TENSOR_NEXTN_POST_PROJ, "weight"), { n_embd, n_embd_backbone }, 0); + + int rope_freqs_flag = 0; + + for (int i = 0; i < n_layer; ++i) { + auto & layer = layers[i]; + + const int64_t n_head = hparams.n_head(i); + const int64_t n_embd_head = hparams.n_embd_head_k(i); + const int64_t n_ff = hparams.n_ff(i); + + if (i == 0) { + nextn_pre_proj = create_tensor(tn(LLM_TENSOR_NEXTN_PRE_PROJ, "weight", i), { 2*n_embd_backbone, n_embd }, 0); + } + + layer.attn_norm = create_tensor(tn(LLM_TENSOR_ATTN_NORM, "weight", i), { n_embd }, 0); + layer.wq = create_tensor(tn(LLM_TENSOR_ATTN_Q, "weight", i), { n_embd, n_embd_head*n_head }, 0); + layer.wo = create_tensor(tn(LLM_TENSOR_ATTN_OUT, "weight", i), { n_embd_head*n_head, n_embd }, 0); + + layer.attn_q_norm = create_tensor(tn(LLM_TENSOR_ATTN_Q_NORM, "weight", i), { n_embd_head }, 0); + layer.attn_post_norm = create_tensor(tn(LLM_TENSOR_ATTN_POST_NORM, "weight", i), { n_embd }, 0); + + layer.out_scale = create_tensor(tn(LLM_TENSOR_LAYER_OUT_SCALE, "weight", i), { 1u }, 0); + + if (!hparams.is_swa(i)) { + layer.rope_freqs = create_tensor(tn(LLM_TENSOR_ROPE_FREQS, "weight", i), { n_embd_head/2 }, rope_freqs_flag); + rope_freqs_flag = TENSOR_DUPLICATED; + } + + layer.ffn_norm = create_tensor(tn(LLM_TENSOR_FFN_NORM, "weight", i), { n_embd }, 0); + layer.ffn_gate = create_tensor(tn(LLM_TENSOR_FFN_GATE, "weight", i), { n_embd, n_ff }, 0); + layer.ffn_up = create_tensor(tn(LLM_TENSOR_FFN_UP, "weight", i), { n_embd, n_ff }, 0); + layer.ffn_down = create_tensor(tn(LLM_TENSOR_FFN_DOWN, "weight", i), { n_ff, n_embd }, 0); + layer.ffn_post_norm = create_tensor(tn(LLM_TENSOR_FFN_POST_NORM, "weight", i), { n_embd }, 0); + } +} + +std::unique_ptr llama_model_gemma4_assistant::build_arch_graph(const llm_graph_params & params) const { + return std::make_unique(*this, params); +} + +llama_model_gemma4_assistant::graph::graph(const llama_model & model, const llm_graph_params & params) : + llm_graph_context(params) { + GGML_ASSERT(src_mctx && "Gemma 4 assistant graph requires an MTP source (llama_set_mtp_source)"); + GGML_ASSERT(src_model && "Gemma 4 assistant graph requires a source model"); + GGML_ASSERT(src_model->tok_embd && "source model missing tok_embd"); + + const auto & src_hparams = src_model->hparams; + + // By convention the MTP draft reads from the trunk's final SWA and full layers. + const int32_t src_layer_full = (int32_t) src_hparams.n_layer() - 1; + const int32_t src_layer_swa = (int32_t) src_hparams.n_layer() - 2; + GGML_ASSERT(!src_hparams.is_swa(src_layer_full) && "trunk's last layer must be full attention"); + GGML_ASSERT( src_hparams.is_swa(src_layer_swa) && "trunk's penultimate layer must be SWA"); + + const int64_t n_embd_backbone = hparams.n_embd_out(); + + ggml_tensor * inp_tokens; + ggml_tensor * inp_h; + { + auto inp = std::make_unique(n_embd_backbone); + + inp->tokens = ggml_new_tensor_1d(ctx0, GGML_TYPE_I32, ubatch.n_tokens); + cb(inp->tokens, "inp_tokens", -1); + ggml_set_input(inp->tokens); + inp_tokens = inp->tokens; + res->t_inp_tokens = inp->tokens; + + inp->embd = ggml_new_tensor_2d(ctx0, GGML_TYPE_F32, n_embd_backbone, ubatch.n_tokens); + cb(inp->embd, "inp_h", -1); + ggml_set_input(inp->embd); + inp_h = inp->embd; + res->t_inp_embd = inp->embd; + + res->add_input(std::move(inp)); + } + + ggml_tensor * x = ggml_get_rows(ctx0, src_model->tok_embd, inp_tokens); + x = ggml_scale(ctx0, x, sqrtf((float) n_embd_backbone)); + cb(x, "inp_embd_target", -1); + + ggml_tensor * xh = ggml_concat(ctx0, x, inp_h, 0); + cb(xh, "inp_xh", -1); + + ggml_tensor * cur = ggml_mul_mat(ctx0, model.nextn_pre_proj, xh); + cb(cur, "pre_proj", -1); + + auto * inp_attn = build_attn_inp_src_kv_iswa(); + ggml_tensor * inp_pos = build_inp_pos(); + ggml_tensor * inp_out_ids = build_inp_out_ids(); + + ggml_tensor * inpL = cur; + + for (int il = 0; il < n_layer; ++il) { + const bool is_swa = hparams.is_swa(il); + const int32_t il_src = is_swa ? src_layer_swa : src_layer_full; + + const int64_t n_embd_head = hparams.n_embd_head_k(il); + const int64_t n_head = hparams.n_head(il); + + const float freq_base_l = model.get_rope_freq_base(cparams, il); + const float freq_scale_l = model.get_rope_freq_scale(cparams, il); + const int n_rot_l = hparams.n_rot(il); + + ggml_tensor * cur_norm = build_norm(inpL, model.layers[il].attn_norm, nullptr, LLM_NORM_RMS, il); + cb(cur_norm, "attn_norm", il); + + ggml_tensor * Qcur = build_lora_mm(model.layers[il].wq, cur_norm); + Qcur = ggml_reshape_3d(ctx0, Qcur, n_embd_head, n_head, n_tokens); + Qcur = build_norm(Qcur, model.layers[il].attn_q_norm, nullptr, LLM_NORM_RMS, il); + cb(Qcur, "Qcur_normed", il); + + ggml_tensor * freq_factors = is_swa ? nullptr : model.layers[il].rope_freqs; + Qcur = ggml_rope_ext(ctx0, Qcur, inp_pos, freq_factors, n_rot_l, rope_type, n_ctx_orig, + freq_base_l, freq_scale_l, ext_factor, attn_factor, beta_fast, beta_slow); + cb(Qcur, "Qcur_pos", il); + + cur = build_attn(inp_attn, model.layers[il].wo, nullptr, nullptr, + Qcur, nullptr, nullptr, nullptr, hparams.f_attention_scale, il, il_src); + + if (il == n_layer - 1 && inp_out_ids) { + cur = ggml_get_rows(ctx0, cur, inp_out_ids); + inpL = ggml_get_rows(ctx0, inpL, inp_out_ids); + } + + cur = build_norm(cur, model.layers[il].attn_post_norm, nullptr, LLM_NORM_RMS, il); + cb(cur, "attn_post_norm", il); + + ggml_tensor * attn_out = ggml_add(ctx0, cur, inpL); + cb(attn_out, "attn_out", il); + + cur = build_norm(attn_out, model.layers[il].ffn_norm, nullptr, LLM_NORM_RMS, il); + cb(cur, "ffn_norm", il); + + cur = build_ffn(cur, + model.layers[il].ffn_up, nullptr, nullptr, + model.layers[il].ffn_gate, nullptr, nullptr, + model.layers[il].ffn_down, nullptr, nullptr, + nullptr, + LLM_FFN_GELU, LLM_FFN_PAR, il); + cb(cur, "ffn_out", il); + + cur = build_norm(cur, model.layers[il].ffn_post_norm, nullptr, LLM_NORM_RMS, -1); + cb(cur, "ffn_post_norm", il); + + cur = ggml_add(ctx0, cur, attn_out); + + cur = ggml_mul(ctx0, cur, model.layers[il].out_scale); + cb(cur, "out_scaled", il); + + inpL = cur; + } + cur = inpL; + + cur = build_norm(cur, model.output_norm, nullptr, LLM_NORM_RMS, -1); + cb(cur, "result_norm", -1); + + ggml_tensor * logits = build_lora_mm(model.output, cur); + cb(logits, "result_output", -1); + res->t_logits = logits; + + ggml_tensor * h_next = ggml_mul_mat(ctx0, model.nextn_post_proj, cur); + cb(h_next, "h_nextn", -1); + res->t_h_nextn = h_next; + + ggml_build_forward_expand(gf, logits); + ggml_build_forward_expand(gf, h_next); +} diff --git a/src/models/gemma4.cpp b/src/models/gemma4.cpp index 31906de33d97..8d8d5cb6c24c 100644 --- a/src/models/gemma4.cpp +++ b/src/models/gemma4.cpp @@ -2,12 +2,12 @@ void llama_model_gemma4::load_arch_hparams(llama_model_loader & ml) { hparams.swa_type = LLAMA_SWA_TYPE_STANDARD; - ml.get_key_or_arr(LLM_KV_ATTENTION_SLIDING_WINDOW_PATTERN, hparams.is_swa_impl, hparams.n_layer); + ml.get_key_or_arr(LLM_KV_ATTENTION_SLIDING_WINDOW_PATTERN, hparams.is_swa_impl, hparams.n_layer()); uint32_t n_kv_shared_layers = 0; ml.get_key(LLM_KV_ATTENTION_SHARED_KV_LAYERS, n_kv_shared_layers, false); - hparams.n_layer_kv_from_start = hparams.n_layer - (int32_t)n_kv_shared_layers; + hparams.n_layer_kv_from_start = hparams.n_layer_all - (int32_t)n_kv_shared_layers; hparams.f_attention_scale = 1.0f; // Gemma4 uses self.scaling = 1.0 (no pre-attn scaling) ml.get_key(LLM_KV_ROPE_FREQ_BASE_SWA, hparams.rope_freq_base_train_swa, false); @@ -19,7 +19,7 @@ void llama_model_gemma4::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_ATTENTION_VALUE_LENGTH_SWA, hparams.n_embd_head_v_swa); ml.get_key(LLM_KV_FINAL_LOGIT_SOFTCAPPING, hparams.f_final_logit_softcapping, false); - switch (hparams.n_layer) { + switch (hparams.n_layer()) { case 30: type = LLM_TYPE_26B_A4B; break; case 35: type = LLM_TYPE_E2B; break; case 42: type = LLM_TYPE_E4B; break; @@ -270,7 +270,8 @@ llama_model_gemma4::graph::graph(const llama_model & model, const llm_graph_para } // TODO @ngxson : strip unused token right after the last KV layer to speed up prompt processing - if (il == n_layer - 1 && inp_out_ids) { + // keep all rows when extracting unmasked nextn embeddings (MTP target needs the hidden state for every token) + if (il == n_layer - 1 && inp_out_ids && cparams.embeddings_nextn_masked) { cur = ggml_get_rows(ctx0, cur, inp_out_ids); inpL = ggml_get_rows(ctx0, inpL, inp_out_ids); } @@ -370,7 +371,7 @@ llama_model_gemma4::graph::graph(const llama_model & model, const llm_graph_para ggml_tensor * inp_this_layer = ggml_view_2d_slice(ctx0, inp_per_layer, il); // [n_embd_per_layer, n_tokens] // TODO @ngxson : improve this - if (il == n_layer - 1 && inp_out_ids) { + if (il == n_layer - 1 && inp_out_ids && cparams.embeddings_nextn_masked) { inp_this_layer = ggml_get_rows(ctx0, inp_this_layer, inp_out_ids); } @@ -401,6 +402,17 @@ llama_model_gemma4::graph::graph(const llama_model & model, const llm_graph_para model.output_norm, nullptr, LLM_NORM_RMS, -1); + // Expose the post-output-norm hidden state (the LM-head input feature) so that + // MTP draft contexts can read it via llama_get_embeddings_nextn_ith() as the + // recurrent h input. This matches the reference (transformers/vLLM/SGLang), + // which feeds the drafter the target's post-final-norm hidden state. + cb(cur, "h_nextn", -1); + res->t_h_nextn = cur; + + if (!cparams.embeddings_nextn_masked && inp_out_ids) { + cur = ggml_get_rows(ctx0, cur, inp_out_ids); + } + cb(cur, "result_norm", -1); res->t_embd = cur; diff --git a/src/models/glm-dsa.cpp b/src/models/glm-dsa.cpp index af2b55ef563d..11d91312defc 100644 --- a/src/models/glm-dsa.cpp +++ b/src/models/glm-dsa.cpp @@ -33,13 +33,10 @@ void llama_model_glm_dsa::load_arch_hparams(llama_model_loader & ml) { } // NextN/MTP parameters - ml.get_key(LLM_KV_NEXTN_PREDICT_LAYERS, hparams.nextn_predict_layers, false); - GGML_ASSERT(hparams.nextn_predict_layers < hparams.n_layer && "nextn_predict_layers must be < n_layer"); + ml.get_key(LLM_KV_NEXTN_PREDICT_LAYERS, hparams.n_layer_nextn, false); + GGML_ASSERT(hparams.n_layer_nextn < hparams.n_layer_all && "n_layer_nextn must be < n_layer_impl"); - // TODO: when MTP is implemented, this should probably be updated if needed - hparams.n_layer_kv_from_start = hparams.n_layer - hparams.nextn_predict_layers; - - switch (hparams.n_layer) { + switch (hparams.n_layer()) { case 79: type = LLM_TYPE_744B_A40B; break; default: type = LLM_TYPE_UNKNOWN; } @@ -76,9 +73,9 @@ void llama_model_glm_dsa::load_arch_tensors(llama_model_loader &) { output = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}, TENSOR_DUPLICATED); } - for (int i = 0; i < n_layer; ++i) { + for (int i = 0; i < n_layer_all; ++i) { int flags = 0; - if (hparams.nextn_predict_layers > 0 && static_cast(i) >= n_layer - hparams.nextn_predict_layers) { + if (i >= n_layer) { // skip all tensors in the NextN layers // TODO @ngxson : TENSOR_NOT_REQUIRED was a hack, need to remove it later flags |= TENSOR_SKIP | TENSOR_NOT_REQUIRED; @@ -135,8 +132,8 @@ void llama_model_glm_dsa::load_arch_tensors(llama_model_loader &) { layer.ffn_up_shexp = create_tensor(tn(LLM_TENSOR_FFN_UP_SHEXP, "weight", i), {n_embd, n_ff_exp * n_expert_shared}, flags); } - // NextN/MTP tensors (preserved but unused) - conditionally load for last nextn_predict_layers - if (hparams.nextn_predict_layers > 0 && static_cast(i) >= n_layer - hparams.nextn_predict_layers) { + // NextN/MTP tensors (preserved but unused) - conditionally load for last n_layer_nextn + if (i >= n_layer) { layer.nextn.eh_proj = create_tensor(tn(LLM_TENSOR_NEXTN_EH_PROJ, "weight", i), { 2 * n_embd, n_embd }, flags); layer.nextn.enorm = create_tensor(tn(LLM_TENSOR_NEXTN_ENORM, "weight", i), { n_embd }, flags); layer.nextn.hnorm = create_tensor(tn(LLM_TENSOR_NEXTN_HNORM, "weight", i), { n_embd }, flags); diff --git a/src/models/glm4-moe.cpp b/src/models/glm4-moe.cpp index 27654b8cba3c..d60e47ddf0c6 100644 --- a/src/models/glm4-moe.cpp +++ b/src/models/glm4-moe.cpp @@ -20,16 +20,13 @@ void llama_model_glm4_moe::load_arch_hparams(llama_model_loader & ml) { } // NextN/MTP parameters - ml.get_key(LLM_KV_NEXTN_PREDICT_LAYERS, hparams.nextn_predict_layers, false); - GGML_ASSERT(hparams.nextn_predict_layers < hparams.n_layer && "nextn_predict_layers must be < n_layer"); + ml.get_key(LLM_KV_NEXTN_PREDICT_LAYERS, hparams.n_layer_nextn, false); + GGML_ASSERT(hparams.n_layer_nextn < hparams.n_layer_all && "n_layer_nextn must be < n_layer_impl"); - // TODO: when MTP is implemented, this should probably be updated if needed - hparams.n_layer_kv_from_start = hparams.n_layer - hparams.nextn_predict_layers; - - switch (hparams.n_layer) { - case 47: type = LLM_TYPE_106B_A12B; break; // GLM-4.5-Air (46 layers + 1 NextN layer) + switch (hparams.n_layer()) { + case 46: type = LLM_TYPE_106B_A12B; break; // GLM-4.5-Air case 48: type = LLM_TYPE_102B_A12B; break; // Solar Open - case 93: type = LLM_TYPE_355B_A32B; break; // GLM-4.5 (92 layers + 1 NextN layer) + case 92: type = LLM_TYPE_355B_A32B; break; // GLM-4.5 default: type = LLM_TYPE_UNKNOWN; } } @@ -54,9 +51,9 @@ void llama_model_glm4_moe::load_arch_tensors(llama_model_loader &) { // Load ALL tensors including NextN layer to satisfy total tensor count // but only PROCESS up to last layer (skipping final NextN layer) in forward pass - for (int i = 0; i < n_layer; ++i) { + for (int i = 0; i < n_layer_all; ++i) { int flags = 0; - if (hparams.nextn_predict_layers > 0 && static_cast(i) >= n_layer - hparams.nextn_predict_layers) { + if (i >= n_layer) { // skip all tensors in the NextN layers flags |= TENSOR_SKIP; } @@ -116,7 +113,7 @@ void llama_model_glm4_moe::load_arch_tensors(llama_model_loader &) { } // NextN/MTP tensors (preserved but unused) - conditionally load for last nextn_predict_layers - if (hparams.nextn_predict_layers > 0 && static_cast(i) >= n_layer - hparams.nextn_predict_layers) { + if (i >= n_layer) { layer.nextn.eh_proj = create_tensor(tn(LLM_TENSOR_NEXTN_EH_PROJ, "weight", i), { 2 * n_embd, n_embd }, flags); layer.nextn.enorm = create_tensor(tn(LLM_TENSOR_NEXTN_ENORM, "weight", i), { n_embd }, flags); layer.nextn.hnorm = create_tensor(tn(LLM_TENSOR_NEXTN_HNORM, "weight", i), { n_embd }, flags); @@ -161,8 +158,7 @@ llama_model_glm4_moe::graph::graph(const llama_model & model, const llm_graph_pa // Only process up to last layer (skip final NextN layer) // Final layer tensors are loaded but not processed in forward pass - const int n_transformer_layers = n_layer - hparams.nextn_predict_layers; - for (int il = 0; il < n_transformer_layers; ++il) { + for (int il = 0; il < n_layer; ++il) { ggml_tensor * inpSA = inpL; // Pre-attention norm @@ -211,7 +207,7 @@ llama_model_glm4_moe::graph::graph(const llama_model & model, const llm_graph_pa model.layers[il].wo, NULL, model.layers[il].wo_s, Qcur, Kcur, Vcur, nullptr, nullptr, nullptr, 1.0f/sqrtf(float(n_embd_head)), il); } - if (il == n_transformer_layers - 1 && inp_out_ids) { + if (il == n_layer - 1 && inp_out_ids) { cur = ggml_get_rows(ctx0, cur, inp_out_ids); inpSA = ggml_get_rows(ctx0, inpSA, inp_out_ids); } diff --git a/src/models/glm4.cpp b/src/models/glm4.cpp index 7c242fed298e..b4326c5f2107 100644 --- a/src/models/glm4.cpp +++ b/src/models/glm4.cpp @@ -5,13 +5,10 @@ void llama_model_glm4::load_arch_hparams(llama_model_loader & ml) { ml.get_key_or_arr(LLM_KV_ROPE_DIMENSION_SECTIONS, hparams.rope_sections, 4, false); // NextN/MTP parameters (GLM-OCR) - ml.get_key(LLM_KV_NEXTN_PREDICT_LAYERS, hparams.nextn_predict_layers, false); - GGML_ASSERT(hparams.nextn_predict_layers < hparams.n_layer && "nextn_predict_layers must be < n_layer"); + ml.get_key(LLM_KV_NEXTN_PREDICT_LAYERS, hparams.n_layer_nextn, false); + GGML_ASSERT(hparams.n_layer_nextn < hparams.n_layer_all && "n_layer_nextn must be < n_layer_impl"); - // TODO: when MTP is implemented, this should probably be updated if needed - hparams.n_layer_kv_from_start = hparams.n_layer - hparams.nextn_predict_layers; - - switch (hparams.n_layer) { + switch (hparams.n_layer()) { case 17: type = LLM_TYPE_1B; break; // GLM-OCR case 40: type = LLM_TYPE_9B; break; case 61: type = LLM_TYPE_32B; break; @@ -32,9 +29,9 @@ void llama_model_glm4::load_arch_tensors(llama_model_loader &) { output = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}, TENSOR_DUPLICATED); } - for (int i = 0; i < n_layer; ++i) { + for (int i = 0; i < n_layer_all; ++i) { int flags = 0; - if (hparams.nextn_predict_layers > 0 && static_cast(i) >= n_layer - hparams.nextn_predict_layers) { + if (i >= n_layer) { // skip all tensors in the NextN layers flags |= TENSOR_SKIP; } @@ -55,7 +52,7 @@ void llama_model_glm4::load_arch_tensors(llama_model_loader &) { layer.ffn_post_norm = create_tensor(tn(LLM_TENSOR_FFN_POST_NORM, "weight", i), {n_embd}, flags); // NextN/MTP tensors (preserved but unused) - conditionally load for last nextn_predict_layers - if (hparams.nextn_predict_layers > 0 && static_cast(i) >= n_layer - hparams.nextn_predict_layers) { + if (i >= n_layer) { layer.nextn.eh_proj = create_tensor(tn(LLM_TENSOR_NEXTN_EH_PROJ, "weight", i), { 2 * n_embd, n_embd }, flags); layer.nextn.enorm = create_tensor(tn(LLM_TENSOR_NEXTN_ENORM, "weight", i), { n_embd }, flags); layer.nextn.hnorm = create_tensor(tn(LLM_TENSOR_NEXTN_HNORM, "weight", i), { n_embd }, flags); @@ -100,8 +97,7 @@ llama_model_glm4::graph::graph(const llama_model & model, const llm_graph_params // Only process up to last layer (skip final NextN layer) // Final layer tensors are loaded but not processed in forward pass - const int n_transformer_layers = n_layer - hparams.nextn_predict_layers; - for (int il = 0; il < n_transformer_layers; ++il) { + for (int il = 0; il < n_layer; ++il) { ggml_tensor * inpSA = inpL; // Pre-attention norm @@ -140,7 +136,7 @@ llama_model_glm4::graph::graph(const llama_model & model, const llm_graph_params model.layers[il].wo, NULL, model.layers[il].wo_s, Qcur, Kcur, Vcur, nullptr, nullptr, nullptr, 1.0f / sqrtf(float(n_embd_head)), il); } - if (il == n_transformer_layers - 1 && inp_out_ids) { + if (il == n_layer - 1 && inp_out_ids) { cur = ggml_get_rows(ctx0, cur, inp_out_ids); inpSA = ggml_get_rows(ctx0, inpSA, inp_out_ids); } diff --git a/src/models/gpt2.cpp b/src/models/gpt2.cpp index e2dcc8b1521e..45afbccc1210 100644 --- a/src/models/gpt2.cpp +++ b/src/models/gpt2.cpp @@ -2,7 +2,8 @@ void llama_model_gpt2::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_ATTENTION_LAYERNORM_EPS, hparams.f_norm_eps); - switch (hparams.n_layer) { + + switch (hparams.n_layer()) { case 12: type = LLM_TYPE_SMALL; break; case 24: type = LLM_TYPE_MEDIUM; break; case 36: type = LLM_TYPE_LARGE; break; diff --git a/src/models/gptneox.cpp b/src/models/gptneox.cpp index 443e35addf28..ed5e8c50da2f 100644 --- a/src/models/gptneox.cpp +++ b/src/models/gptneox.cpp @@ -3,7 +3,8 @@ void llama_model_gptneox::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_ATTENTION_LAYERNORM_EPS, hparams.f_norm_eps); ml.get_key(LLM_KV_USE_PARALLEL_RESIDUAL, hparams.use_par_res); - switch (hparams.n_layer) { + + switch (hparams.n_layer()) { case 6: switch (hparams.n_ff()) { case 512: type = LLM_TYPE_14M; break; diff --git a/src/models/granite-hybrid.cpp b/src/models/granite-hybrid.cpp index 8740d9fc7d9b..eb23095aece6 100644 --- a/src/models/granite-hybrid.cpp +++ b/src/models/granite-hybrid.cpp @@ -19,7 +19,7 @@ void llama_model_granite_hybrid::load_arch_hparams(llama_model_loader & ml) { hparams.rope_finetuned = rope_finetuned; // A layer is recurrent IFF the n_head_kv value is set to 0 - for (uint32_t i = 0; i < hparams.n_layer; ++i) { + for (uint32_t i = 0; i < hparams.n_layer(); ++i) { hparams.is_recr_impl[i] = hparams.n_head_kv(i) == 0; } diff --git a/src/models/granite-moe.cpp b/src/models/granite-moe.cpp index 0d89bc1f3404..115263c418fa 100644 --- a/src/models/granite-moe.cpp +++ b/src/models/granite-moe.cpp @@ -12,7 +12,7 @@ void llama_model_granite_moe::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_ROPE_SCALING_FINETUNED, rope_finetuned, false); hparams.rope_finetuned = rope_finetuned; - switch (hparams.n_layer) { + switch (hparams.n_layer()) { case 32: type = LLM_TYPE_3B; break; case 40: type = LLM_TYPE_3B; break; // Add additional layer/vocab/etc checks here for other model sizes diff --git a/src/models/granite.cpp b/src/models/granite.cpp index cda4aa231fa9..7aff942da015 100644 --- a/src/models/granite.cpp +++ b/src/models/granite.cpp @@ -12,7 +12,7 @@ void llama_model_granite::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_ROPE_SCALING_FINETUNED, rope_finetuned, false); hparams.rope_finetuned = rope_finetuned; - switch (hparams.n_layer) { + switch (hparams.n_layer()) { case 32: type = LLM_TYPE_3B; break; case 40: type = LLM_TYPE_3B; break; // Add additional layer/vocab/etc checks here for other model sizes diff --git a/src/models/grok.cpp b/src/models/grok.cpp index 7c46ec1c0f2d..42f38af67243 100644 --- a/src/models/grok.cpp +++ b/src/models/grok.cpp @@ -26,7 +26,7 @@ void llama_model_grok::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_ROPE_SCALING_YARN_BETA_FAST, hparams.yarn_beta_fast, false); ml.get_key(LLM_KV_ROPE_SCALING_YARN_BETA_SLOW, hparams.yarn_beta_slow, false); - switch (hparams.n_layer) { + switch (hparams.n_layer()) { case 64: type = LLM_TYPE_314B; break; default: type = LLM_TYPE_UNKNOWN; } diff --git a/src/models/grovemoe.cpp b/src/models/grovemoe.cpp index 1cab75adc7fe..643a448e59ac 100644 --- a/src/models/grovemoe.cpp +++ b/src/models/grovemoe.cpp @@ -7,7 +7,7 @@ void llama_model_grovemoe::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_EXPERTS_PER_GROUP, hparams.n_group_experts); ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps); - switch (hparams.n_layer) { + switch (hparams.n_layer()) { case 48: type = LLM_TYPE_30B_A3B; break; default: type = LLM_TYPE_UNKNOWN; } diff --git a/src/models/hunyuan-moe.cpp b/src/models/hunyuan-moe.cpp index deb3c9671f33..4d55f5e7f317 100644 --- a/src/models/hunyuan-moe.cpp +++ b/src/models/hunyuan-moe.cpp @@ -5,7 +5,7 @@ void llama_model_hunyuan_moe::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_EXPERT_FEED_FORWARD_LENGTH, hparams.n_ff_exp); ml.get_key(LLM_KV_EXPERT_SHARED_FEED_FORWARD_LENGTH, hparams.n_ff_shexp, false); - switch (hparams.n_layer) { + switch (hparams.n_layer()) { case 32: type = LLM_TYPE_A13B; break; default: type = LLM_TYPE_UNKNOWN; } diff --git a/src/models/internlm2.cpp b/src/models/internlm2.cpp index f9ee37a24b69..f6cfdfb9458f 100644 --- a/src/models/internlm2.cpp +++ b/src/models/internlm2.cpp @@ -2,7 +2,8 @@ void llama_model_internlm2::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps); - switch (hparams.n_layer) { + + switch (hparams.n_layer()) { case 32: type = LLM_TYPE_7B; break; case 48: type = LLM_TYPE_20B; break; default: type = LLM_TYPE_UNKNOWN; diff --git a/src/models/jais.cpp b/src/models/jais.cpp index 2ba162605f13..415103ce23a8 100644 --- a/src/models/jais.cpp +++ b/src/models/jais.cpp @@ -4,7 +4,7 @@ void llama_model_jais::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_ATTENTION_LAYERNORM_EPS, hparams.f_norm_eps); ml.get_key(LLM_KV_ATTENTION_MAX_ALIBI_BIAS, hparams.f_max_alibi_bias, false); - switch (hparams.n_layer) { + switch (hparams.n_layer()) { case 24: type = LLM_TYPE_1_3B; break; case 40: type = LLM_TYPE_13B; break; /* TODO: add variants */ diff --git a/src/models/jais2.cpp b/src/models/jais2.cpp index 8966131441c3..8610fcc9f82f 100644 --- a/src/models/jais2.cpp +++ b/src/models/jais2.cpp @@ -3,7 +3,7 @@ void llama_model_jais2::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_ATTENTION_LAYERNORM_EPS, hparams.f_norm_eps); - switch (hparams.n_layer) { + switch (hparams.n_layer()) { case 32: type = LLM_TYPE_8B; break; case 68: type = LLM_TYPE_70B; break; default: type = LLM_TYPE_UNKNOWN; diff --git a/src/models/jamba.cpp b/src/models/jamba.cpp index a62b121b3eea..dba160b014fd 100644 --- a/src/models/jamba.cpp +++ b/src/models/jamba.cpp @@ -8,11 +8,11 @@ void llama_model_jamba::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps); - for (uint32_t i = 0; i < hparams.n_layer; ++i) { + for (uint32_t i = 0; i < hparams.n_layer(); ++i) { hparams.is_recr_impl[i] = hparams.n_head_kv(i) == 0; } - switch (hparams.n_layer) { + switch (hparams.n_layer()) { // TODO: Jamba layers are a bit heterogeneous, so naming this is hard. case 12: // 900M 8x???M case 32: // 51B 16x?B diff --git a/src/models/jina-bert-v2.cpp b/src/models/jina-bert-v2.cpp index 4f8866ece4d2..86ff1c84d1a6 100644 --- a/src/models/jina-bert-v2.cpp +++ b/src/models/jina-bert-v2.cpp @@ -4,7 +4,7 @@ void llama_model_jina_bert_v2::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_ATTENTION_LAYERNORM_EPS, hparams.f_norm_eps); hparams.f_max_alibi_bias = 8.0f; - switch (hparams.n_layer) { + switch (hparams.n_layer()) { case 4: type = LLM_TYPE_33M; break; // jina-embeddings-small case 12: type = LLM_TYPE_137M; break; // jina-embeddings-base default: type = LLM_TYPE_UNKNOWN; diff --git a/src/models/jina-bert-v3.cpp b/src/models/jina-bert-v3.cpp index e0527529f56c..1c974a6f16cc 100644 --- a/src/models/jina-bert-v3.cpp +++ b/src/models/jina-bert-v3.cpp @@ -3,7 +3,7 @@ void llama_model_jina_bert_v3::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_ATTENTION_LAYERNORM_EPS, hparams.f_norm_eps); - switch (hparams.n_layer) { + switch (hparams.n_layer()) { case 24: type = LLM_TYPE_558M; break; default: type = LLM_TYPE_UNKNOWN; diff --git a/src/models/kimi-linear.cpp b/src/models/kimi-linear.cpp index c13f71b5bcb1..367f6990d1fb 100644 --- a/src/models/kimi-linear.cpp +++ b/src/models/kimi-linear.cpp @@ -14,7 +14,7 @@ void llama_model_kimi_linear::load_arch_hparams(llama_model_loader & ml) { // Mark KDA layers as recurrent using n_head_kv pattern (like Jamba) // Set n_head_kv = 0 for KDA layers (recurrent), n_head_kv = n_head for MLA layers (attention) - for (uint32_t i = 0; i < hparams.n_layer; ++i) { + for (uint32_t i = 0; i < hparams.n_layer(); ++i) { hparams.is_recr_impl[i] = hparams.n_head_kv(i) == 0; // KDA layers are recurrent } @@ -25,7 +25,7 @@ void llama_model_kimi_linear::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_EXPERT_WEIGHTS_SCALE, hparams.expert_weights_scale, false); ml.get_key(LLM_KV_EXPERT_GATING_FUNC, hparams.expert_gating_func); - switch (hparams.n_layer) { + switch (hparams.n_layer()) { case 27: type = LLM_TYPE_48B_A3B; break; // Kimi-Linear-48B-A3B default: type = LLM_TYPE_UNKNOWN; } diff --git a/src/models/lfm2.cpp b/src/models/lfm2.cpp index 3898b56bb12d..97da8a6abb84 100644 --- a/src/models/lfm2.cpp +++ b/src/models/lfm2.cpp @@ -5,10 +5,13 @@ void llama_model_lfm2::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_SHORTCONV_L_CACHE, hparams.n_shortconv_l_cache); ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps); - for (uint32_t il = 0; il < hparams.n_layer; ++il) { + + for (uint32_t il = 0; il < hparams.n_layer(); ++il) { hparams.is_recr_impl[il] = hparams.n_head_kv(il) == 0; } - hparams.n_layer_dense_lead = hparams.n_layer; + + hparams.n_layer_dense_lead = hparams.n_layer(); + switch (hparams.n_ff()) { case 4608: type = LLM_TYPE_350M; break; case 6912: type = LLM_TYPE_700M; break; @@ -16,9 +19,10 @@ void llama_model_lfm2::load_arch_hparams(llama_model_loader & ml) { case 10752: type = LLM_TYPE_2_6B; break; default: type = LLM_TYPE_UNKNOWN; } + if (const auto is_swa = ml.get_key(LLM_KV_ATTENTION_SLIDING_WINDOW, hparams.n_swa, false); is_swa && hparams.n_swa > 0) { hparams.swa_type = LLAMA_SWA_TYPE_STANDARD; - for (uint32_t il = 0; il < hparams.n_layer; ++il) { + for (uint32_t il = 0; il < hparams.n_layer(); ++il) { hparams.is_swa_impl[il] = !hparams.is_recr_impl[il]; } } diff --git a/src/models/lfm2moe.cpp b/src/models/lfm2moe.cpp index 81ced2eaba2f..490f5c223ebb 100644 --- a/src/models/lfm2moe.cpp +++ b/src/models/lfm2moe.cpp @@ -9,11 +9,11 @@ void llama_model_lfm2moe::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_EXPERT_FEED_FORWARD_LENGTH, hparams.n_ff_exp); ml.get_key(LLM_KV_EXPERT_GATING_FUNC, hparams.expert_gating_func); - for (uint32_t il = 0; il < hparams.n_layer; ++il) { + for (uint32_t il = 0; il < hparams.n_layer(); ++il) { hparams.is_recr_impl[il] = hparams.n_head_kv(il) == 0; } - switch (hparams.n_layer) { + switch (hparams.n_layer()) { case 24: type = LLM_TYPE_8B_A1B; break; case 40: type = LLM_TYPE_24B_A2B; break; default: type = LLM_TYPE_UNKNOWN; diff --git a/src/models/llada-moe.cpp b/src/models/llada-moe.cpp index 9722dde9f177..2ae893864472 100644 --- a/src/models/llada-moe.cpp +++ b/src/models/llada-moe.cpp @@ -2,11 +2,12 @@ void llama_model_llada_moe::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_EXPERT_FEED_FORWARD_LENGTH, hparams.n_ff_exp, false); - ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps); + // diffusion language model uses non-causal attention hparams.causal_attn = false; - switch (hparams.n_layer) { + + switch (hparams.n_layer()) { case 16: type = LLM_TYPE_A1_7B; break; default: type = LLM_TYPE_UNKNOWN; } diff --git a/src/models/llada.cpp b/src/models/llada.cpp index 58b2c466e176..87d4259f9a74 100644 --- a/src/models/llada.cpp +++ b/src/models/llada.cpp @@ -2,14 +2,16 @@ void llama_model_llada::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps); + // LLaDA-8B has 32 layers, similar to LLaMA but for diffusion - switch (hparams.n_layer) { + switch (hparams.n_layer()) { case 32: type = LLM_TYPE_8B; break; default: type = LLM_TYPE_UNKNOWN; } + // Set non-causal attention for diffusion models hparams.causal_attn = false; } diff --git a/src/models/llama.cpp b/src/models/llama.cpp index cef66d054b0c..c0ec7e0a9adb 100644 --- a/src/models/llama.cpp +++ b/src/models/llama.cpp @@ -7,13 +7,13 @@ void llama_model_llama::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps); if (hparams.n_expert == 8) { - switch (hparams.n_layer) { + switch (hparams.n_layer()) { case 32: type = LLM_TYPE_8x7B; break; case 56: type = LLM_TYPE_8x22B; break; default: type = LLM_TYPE_UNKNOWN; } } else { - switch (hparams.n_layer) { + switch (hparams.n_layer()) { case 16: type = LLM_TYPE_1B; break; // Llama 3.2 1B case 22: type = LLM_TYPE_1B; break; case 26: type = LLM_TYPE_3B; break; diff --git a/src/models/llama4.cpp b/src/models/llama4.cpp index 8f39b3f59a5b..7194c72a5850 100644 --- a/src/models/llama4.cpp +++ b/src/models/llama4.cpp @@ -8,7 +8,7 @@ void llama_model_llama4::load_arch_hparams(llama_model_loader & ml) { const bool found_swa = ml.get_key(LLM_KV_ATTENTION_SLIDING_WINDOW, hparams.n_swa, false); if (found_swa && hparams.n_swa == 0) { hparams.swa_type = LLAMA_SWA_TYPE_NONE; - hparams.n_no_rope_layer_step = hparams.n_layer; // always use rope + hparams.n_no_rope_layer_step = hparams.n_layer(); // always use rope } else { hparams.swa_type = LLAMA_SWA_TYPE_CHUNKED; hparams.n_swa = 8192; diff --git a/src/models/maincoder.cpp b/src/models/maincoder.cpp index 84cfe399027e..ae56a26a1f64 100644 --- a/src/models/maincoder.cpp +++ b/src/models/maincoder.cpp @@ -2,7 +2,8 @@ void llama_model_maincoder::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps); - switch (hparams.n_layer) { + + switch (hparams.n_layer()) { case 32: type = LLM_TYPE_1B; break; default: type = LLM_TYPE_UNKNOWN; } diff --git a/src/models/mamba.cpp b/src/models/mamba.cpp index 887a1fa509a9..0d94e98281ce 100644 --- a/src/models/mamba.cpp +++ b/src/models/mamba.cpp @@ -9,7 +9,7 @@ void llama_model_mamba::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps); - switch (hparams.n_layer) { + switch (hparams.n_layer()) { case 24: switch (hparams.n_embd) { case 768: type = LLM_TYPE_SMALL; break; diff --git a/src/models/mamba2.cpp b/src/models/mamba2.cpp index 3277ca53ec4b..c5951cf0f7fc 100644 --- a/src/models/mamba2.cpp +++ b/src/models/mamba2.cpp @@ -9,7 +9,7 @@ void llama_model_mamba2::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps); - switch (hparams.n_layer) { + switch (hparams.n_layer()) { case 24: switch (hparams.n_embd) { case 768: type = LLM_TYPE_SMALL; break; diff --git a/src/models/mellum.cpp b/src/models/mellum.cpp index 1e1e97e9fa01..28823018bc0b 100644 --- a/src/models/mellum.cpp +++ b/src/models/mellum.cpp @@ -13,7 +13,7 @@ void llama_model_mellum::load_arch_hparams(llama_model_loader & ml) { if (res) { hparams.set_swa_pattern(swa_period); } else { - ml.get_key_or_arr(LLM_KV_ATTENTION_SLIDING_WINDOW_PATTERN, hparams.is_swa_impl, hparams.n_layer); + ml.get_key_or_arr(LLM_KV_ATTENTION_SLIDING_WINDOW_PATTERN, hparams.is_swa_impl, hparams.n_layer()); } hparams.rope_freq_base_train_swa = hparams.rope_freq_base_train; @@ -24,7 +24,7 @@ void llama_model_mellum::load_arch_hparams(llama_model_loader & ml) { hparams.swa_type = LLAMA_SWA_TYPE_NONE; } - switch (hparams.n_layer) { + switch (hparams.n_layer()) { case 28: type = LLM_TYPE_12B_A2_5B; break; default: type = LLM_TYPE_UNKNOWN; } diff --git a/src/models/mimo2.cpp b/src/models/mimo2.cpp index 1bcdf696f2e8..889891605701 100644 --- a/src/models/mimo2.cpp +++ b/src/models/mimo2.cpp @@ -9,18 +9,17 @@ void llama_model_mimo2::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_ATTENTION_SLIDING_WINDOW, hparams.n_swa); ml.get_key(LLM_KV_ROPE_FREQ_BASE_SWA, hparams.rope_freq_base_train_swa, false); - ml.get_key_or_arr(LLM_KV_ATTENTION_SLIDING_WINDOW_PATTERN, hparams.is_swa_impl, hparams.n_layer); + ml.get_key_or_arr(LLM_KV_ATTENTION_SLIDING_WINDOW_PATTERN, hparams.is_swa_impl, hparams.n_layer()); float value_scale = 0.0f; if (ml.get_key(LLM_KV_ATTENTION_VALUE_SCALE, value_scale, false) && value_scale != 1.0f) { hparams.f_attn_value_scale = value_scale; } - ml.get_key(LLM_KV_NEXTN_PREDICT_LAYERS, hparams.nextn_predict_layers, false); - GGML_ASSERT(hparams.nextn_predict_layers < hparams.n_layer && "nextn_predict_layers must be < n_layer"); - hparams.n_layer_kv_from_start = hparams.n_layer - hparams.nextn_predict_layers; + ml.get_key(LLM_KV_NEXTN_PREDICT_LAYERS, hparams.n_layer_nextn, false); + GGML_ASSERT(hparams.n_layer_nextn < hparams.n_layer_all && "n_layer_nextn must be < n_layer_impl"); - switch (hparams.n_layer - hparams.nextn_predict_layers) { + switch (hparams.n_layer()) { case 48: type = LLM_TYPE_310B_A15B; break; default: type = LLM_TYPE_UNKNOWN; } @@ -35,16 +34,14 @@ void llama_model_mimo2::load_arch_tensors(llama_model_loader &) { output_norm = create_tensor(tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}, 0); output = create_tensor(tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}, 0); - const uint32_t n_nextn = hparams.nextn_predict_layers; - - for (int i = 0; i < n_layer; ++i) { + for (int i = 0; i < n_layer_all; ++i) { auto & layer = layers[i]; uint32_t n_embd_k_gqa = hparams.n_embd_k_gqa(i); uint32_t n_embd_v_gqa = hparams.n_embd_v_gqa(i); uint32_t n_head = hparams.n_head(i); // NextN/MTP layers (the last n_nextn blocks) are preserved but disabled pending support - const bool is_nextn = (n_nextn > 0) && (static_cast(i) >= n_layer - n_nextn); + const bool is_nextn = i >= n_layer; const int skip = is_nextn ? TENSOR_SKIP : 0; create_tensor_qkv(layer, i, n_embd, n_embd_head_k * n_head, n_embd_k_gqa, n_embd_v_gqa, skip); @@ -93,10 +90,7 @@ llama_model_mimo2::graph::graph(const llama_model & model, const llm_graph_param const float v_scale = hparams.f_attn_value_scale; - // The last hparams.nextn_predict_layers blocks are MTP heads, currently inactive - const int n_transformer_layers = n_layer - hparams.nextn_predict_layers; - - for (int il = 0; il < n_transformer_layers; ++il) { + for (int il = 0; il < n_layer; ++il) { ggml_tensor * inpSA = inpL; uint32_t n_head_l = hparams.n_head(il); @@ -174,7 +168,7 @@ llama_model_mimo2::graph::graph(const llama_model & model, const llm_graph_param } } - if (il == n_transformer_layers - 1 && inp_out_ids) { + if (il == n_layer - 1 && inp_out_ids) { cur = ggml_get_rows(ctx0, cur, inp_out_ids); inpSA = ggml_get_rows(ctx0, inpSA, inp_out_ids); } diff --git a/src/models/minicpm.cpp b/src/models/minicpm.cpp index 966d3af615c0..fc3e5b171d52 100644 --- a/src/models/minicpm.cpp +++ b/src/models/minicpm.cpp @@ -3,7 +3,7 @@ void llama_model_minicpm::load_arch_hparams(llama_model_loader & ml) { // Backward-compatible defaults for older MiniCPM GGUFs hparams.f_embedding_scale = 12.0f; - hparams.f_residual_scale = 1.4f / sqrtf(float(hparams.n_layer)); + hparams.f_residual_scale = 1.4f / sqrtf(float(hparams.n_layer())); hparams.f_logit_scale = hparams.n_embd ? (256.0f / float(hparams.n_embd)) : 1.0f; ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps); @@ -16,7 +16,7 @@ void llama_model_minicpm::load_arch_hparams(llama_model_loader & ml) { // MiniCPM uses rope by default, unlike Granite which uses it as a switch hparams.rope_finetuned = true; - switch (hparams.n_layer) { + switch (hparams.n_layer()) { case 52: type = LLM_TYPE_1B; break; case 40: type = LLM_TYPE_2B; break; default: type = LLM_TYPE_UNKNOWN; diff --git a/src/models/minicpm3.cpp b/src/models/minicpm3.cpp index 1ffc54fa7c66..e011b1ff0a84 100644 --- a/src/models/minicpm3.cpp +++ b/src/models/minicpm3.cpp @@ -5,7 +5,7 @@ void llama_model_minicpm3::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_ATTENTION_Q_LORA_RANK, hparams.n_lora_q); ml.get_key(LLM_KV_ATTENTION_KV_LORA_RANK, hparams.n_lora_kv); - switch (hparams.n_layer) { + switch (hparams.n_layer()) { case 62: type = LLM_TYPE_4B; break; default: type = LLM_TYPE_UNKNOWN; } diff --git a/src/models/minimax-m2.cpp b/src/models/minimax-m2.cpp index 22e291d73a33..b25435e4d97c 100644 --- a/src/models/minimax-m2.cpp +++ b/src/models/minimax-m2.cpp @@ -5,7 +5,7 @@ void llama_model_minimax_m2::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_EXPERT_FEED_FORWARD_LENGTH, hparams.n_ff_exp); ml.get_key(LLM_KV_EXPERT_GATING_FUNC, hparams.expert_gating_func, false); - switch (hparams.n_layer) { + switch (hparams.n_layer()) { case 62: type = LLM_TYPE_230B_A10B; break; default: type = LLM_TYPE_UNKNOWN; } diff --git a/src/models/mistral3.cpp b/src/models/mistral3.cpp index 1ac5a95ccdc5..9a8e3f9a50b7 100644 --- a/src/models/mistral3.cpp +++ b/src/models/mistral3.cpp @@ -18,7 +18,7 @@ void llama_model_mistral3::load_arch_hparams(llama_model_loader & ml) { } } - switch (hparams.n_layer) { + switch (hparams.n_layer()) { case 26: type = LLM_TYPE_3B; break; case 34: type = LLM_TYPE_8B; break; case 40: type = LLM_TYPE_14B; break; diff --git a/src/models/models.h b/src/models/models.h index 866e0d0be3ed..c137e32e8fd1 100644 --- a/src/models/models.h +++ b/src/models/models.h @@ -822,6 +822,19 @@ struct llama_model_gemma4 : public llama_model_base { }; +struct llama_model_gemma4_assistant : public llama_model_base { + llama_model_gemma4_assistant(const struct llama_model_params & params) : llama_model_base(params) {} + void load_arch_hparams(llama_model_loader & ml) override; + void load_arch_tensors(llama_model_loader & ml) override; + + struct graph : public llm_graph_context { + graph(const llama_model & model, const llm_graph_params & params); + }; + + std::unique_ptr build_arch_graph(const llm_graph_params & params) const override; +}; + + struct llama_model_gemma_embedding : public llama_model_base { llama_model_gemma_embedding(const struct llama_model_params & params) : llama_model_base(params) {} void load_arch_hparams(llama_model_loader & ml) override; diff --git a/src/models/modern-bert.cpp b/src/models/modern-bert.cpp index 5ab51867cc03..f3e9407e0125 100644 --- a/src/models/modern-bert.cpp +++ b/src/models/modern-bert.cpp @@ -22,7 +22,7 @@ void llama_model_modern_bert::load_arch_hparams(llama_model_loader & ml) { hparams.llm_ffn_op = llm_ffn_op_type_from_string(hidden_act, LLM_FFN_GEGLU); } - switch (hparams.n_layer) { + switch (hparams.n_layer()) { case 12: type = LLM_TYPE_47M; break; // granite-embedding-small case 22: diff --git a/src/models/mpt.cpp b/src/models/mpt.cpp index 0229d20ed369..d094fd9f80bc 100644 --- a/src/models/mpt.cpp +++ b/src/models/mpt.cpp @@ -5,7 +5,7 @@ void llama_model_mpt::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_ATTENTION_CLAMP_KQV, hparams.f_clamp_kqv, false); ml.get_key(LLM_KV_ATTENTION_MAX_ALIBI_BIAS, hparams.f_max_alibi_bias, false); - switch (hparams.n_layer) { + switch (hparams.n_layer()) { case 32: type = LLM_TYPE_7B; break; case 48: type = LLM_TYPE_30B; break; default: type = LLM_TYPE_UNKNOWN; diff --git a/src/models/nemotron-h.cpp b/src/models/nemotron-h.cpp index d2c811d2497c..a456269347b9 100644 --- a/src/models/nemotron-h.cpp +++ b/src/models/nemotron-h.cpp @@ -9,7 +9,7 @@ void llama_model_nemotron_h::load_arch_hparams(llama_model_loader & ml) { // A layer is recurrent IFF the n_head_kv value is set to 0 and // the n_ff value is set to 0 - for (uint32_t i = 0; i < hparams.n_layer; ++i) { + for (uint32_t i = 0; i < hparams.n_layer(); ++i) { hparams.is_recr_impl[i] = (hparams.n_head_kv(i) == 0 && hparams.n_ff(i) == 0); } @@ -22,7 +22,7 @@ void llama_model_nemotron_h::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_EXPERT_WEIGHTS_SCALE, hparams.expert_weights_scale, false); ml.get_key(LLM_KV_MOE_LATENT_SIZE, hparams.moe_latent_size, false); - switch (hparams.n_layer) { + switch (hparams.n_layer()) { case 52: type = LLM_TYPE_31B_A3_5B; break; // Nemotron-H_MOE 31B case 56: type = LLM_TYPE_9B; break; case 88: type = LLM_TYPE_120B_A12B; break; diff --git a/src/models/nemotron.cpp b/src/models/nemotron.cpp index 5d4a3b5c69e5..6e2bd9a33ca8 100644 --- a/src/models/nemotron.cpp +++ b/src/models/nemotron.cpp @@ -2,7 +2,8 @@ void llama_model_nemotron::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_ATTENTION_LAYERNORM_EPS, hparams.f_norm_eps); - switch (hparams.n_layer) { + + switch (hparams.n_layer()) { case 32: type = LLM_TYPE_4B; break; default: type = LLM_TYPE_UNKNOWN; } diff --git a/src/models/neo-bert.cpp b/src/models/neo-bert.cpp index f00d6eddfc99..4a08d7abd40f 100644 --- a/src/models/neo-bert.cpp +++ b/src/models/neo-bert.cpp @@ -3,7 +3,7 @@ void llama_model_neo_bert::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps); - if (hparams.n_layer == 28) { + if (hparams.n_layer() == 28) { type = LLM_TYPE_250M; } } diff --git a/src/models/nomic-bert-moe.cpp b/src/models/nomic-bert-moe.cpp index a17abe2c2692..da4b62919bb9 100644 --- a/src/models/nomic-bert-moe.cpp +++ b/src/models/nomic-bert-moe.cpp @@ -4,7 +4,7 @@ void llama_model_nomic_bert_moe::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_ATTENTION_LAYERNORM_EPS, hparams.f_norm_eps); ml.get_key(LLM_KV_MOE_EVERY_N_LAYERS, hparams.moe_every_n_layers, 0); - if (hparams.n_layer == 12 && hparams.n_embd == 768) { + if (hparams.n_layer() == 12 && hparams.n_embd == 768) { if (arch == LLM_ARCH_NOMIC_BERT) { type = LLM_TYPE_137M; } else if (arch == LLM_ARCH_NOMIC_BERT_MOE && hparams.moe_every_n_layers == 2) { diff --git a/src/models/nomic-bert.cpp b/src/models/nomic-bert.cpp index 5a8a5584457e..e7fc72286a6d 100644 --- a/src/models/nomic-bert.cpp +++ b/src/models/nomic-bert.cpp @@ -4,7 +4,7 @@ void llama_model_nomic_bert::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_ATTENTION_LAYERNORM_EPS, hparams.f_norm_eps); ml.get_key(LLM_KV_MOE_EVERY_N_LAYERS, hparams.moe_every_n_layers, 0); - if (hparams.n_layer == 12 && hparams.n_embd == 768) { + if (hparams.n_layer() == 12 && hparams.n_embd == 768) { if (arch == LLM_ARCH_NOMIC_BERT) { type = LLM_TYPE_137M; } else if (arch == LLM_ARCH_NOMIC_BERT_MOE && hparams.moe_every_n_layers == 2) { diff --git a/src/models/olmo.cpp b/src/models/olmo.cpp index cfcf17bcb035..9f7a2ba60efb 100644 --- a/src/models/olmo.cpp +++ b/src/models/olmo.cpp @@ -4,7 +4,7 @@ void llama_model_olmo::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_ATTENTION_LAYERNORM_EPS, hparams.f_norm_eps); ml.get_key(LLM_KV_ATTENTION_CLAMP_KQV, hparams.f_clamp_kqv, false); - switch (hparams.n_layer) { + switch (hparams.n_layer()) { case 22: type = LLM_TYPE_1B; break; case 32: type = LLM_TYPE_7B; break; case 80: type = LLM_TYPE_70B; break; diff --git a/src/models/olmo2.cpp b/src/models/olmo2.cpp index 7cc262f55046..cb52cdef7204 100644 --- a/src/models/olmo2.cpp +++ b/src/models/olmo2.cpp @@ -17,7 +17,7 @@ void llama_model_olmo2::load_arch_hparams(llama_model_loader & ml) { hparams.swa_type = LLAMA_SWA_TYPE_NONE; } - switch (hparams.n_layer) { + switch (hparams.n_layer()) { case 16: type = LLM_TYPE_1B; break; case 32: type = LLM_TYPE_7B; break; case 40: type = LLM_TYPE_13B; break; diff --git a/src/models/olmoe.cpp b/src/models/olmoe.cpp index 7976ae44a51c..1e2baeb207ff 100644 --- a/src/models/olmoe.cpp +++ b/src/models/olmoe.cpp @@ -2,7 +2,8 @@ void llama_model_olmoe::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps); - switch (hparams.n_layer) { + + switch (hparams.n_layer()) { case 16: type = LLM_TYPE_A1_7B; break; default: type = LLM_TYPE_UNKNOWN; } diff --git a/src/models/openai-moe.cpp b/src/models/openai-moe.cpp index 15b6c8c12057..3ab15d61f08c 100644 --- a/src/models/openai-moe.cpp +++ b/src/models/openai-moe.cpp @@ -14,7 +14,7 @@ void llama_model_openai_moe::load_arch_hparams(llama_model_loader & ml) { hparams.rope_freq_scale_train_swa = hparams.rope_freq_scale_train; ml.get_key(LLM_KV_ROPE_FREQ_BASE_SWA, hparams.rope_freq_base_train_swa, false); - switch (hparams.n_layer) { + switch (hparams.n_layer()) { case 24: type = LLM_TYPE_20B; break; case 36: type = LLM_TYPE_120B; break; default: type = LLM_TYPE_UNKNOWN; diff --git a/src/models/openelm.cpp b/src/models/openelm.cpp index 9f76350fd4d1..13120bd3236d 100644 --- a/src/models/openelm.cpp +++ b/src/models/openelm.cpp @@ -3,12 +3,12 @@ void llama_model_openelm::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps); - switch (hparams.n_layer) { - case 16: type = LLM_TYPE_270M; break; - case 20: type = LLM_TYPE_450M; break; - case 28: type = LLM_TYPE_1B; break; - case 36: type = LLM_TYPE_3B; break; - default: type = LLM_TYPE_UNKNOWN; + switch (hparams.n_layer()) { + case 16: type = LLM_TYPE_270M; break; + case 20: type = LLM_TYPE_450M; break; + case 28: type = LLM_TYPE_1B; break; + case 36: type = LLM_TYPE_3B; break; + default: type = LLM_TYPE_UNKNOWN; } } diff --git a/src/models/orion.cpp b/src/models/orion.cpp index bcb4bbba4b10..863a2822269b 100644 --- a/src/models/orion.cpp +++ b/src/models/orion.cpp @@ -3,7 +3,7 @@ void llama_model_orion::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_ATTENTION_LAYERNORM_EPS, hparams.f_norm_eps); - switch (hparams.n_layer) { + switch (hparams.n_layer()) { case 40: type = LLM_TYPE_14B; break; default: type = LLM_TYPE_UNKNOWN; } diff --git a/src/models/pangu-embed.cpp b/src/models/pangu-embed.cpp index 7593f879b24f..90f05c088c10 100644 --- a/src/models/pangu-embed.cpp +++ b/src/models/pangu-embed.cpp @@ -2,7 +2,8 @@ void llama_model_pangu_embed::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps); - switch (hparams.n_layer) { + + switch (hparams.n_layer()) { case 26: type = LLM_TYPE_1B; break; // openPangu-Embedded-1B-V1.1 case 34: type = LLM_TYPE_7B; break; // openPangu-Embedded-7B-V1.1 default: type = LLM_TYPE_UNKNOWN; diff --git a/src/models/phi2.cpp b/src/models/phi2.cpp index 8f3ed5f7b7d2..81b1ad12cc02 100644 --- a/src/models/phi2.cpp +++ b/src/models/phi2.cpp @@ -3,7 +3,7 @@ void llama_model_phi2::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_ATTENTION_LAYERNORM_EPS, hparams.f_norm_eps); - switch (hparams.n_layer) { + switch (hparams.n_layer()) { case 24: type = LLM_TYPE_1B; break; case 32: type = LLM_TYPE_3B; break; default: type = LLM_TYPE_UNKNOWN; diff --git a/src/models/phi3.cpp b/src/models/phi3.cpp index f8a4a4d5aa50..716ff814cc12 100644 --- a/src/models/phi3.cpp +++ b/src/models/phi3.cpp @@ -3,7 +3,7 @@ void llama_model_phi3::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps); - switch (hparams.n_layer) { + switch (hparams.n_layer()) { case 24: type = LLM_TYPE_1B; break; case 32: type = LLM_TYPE_3B; break; case 40: type = LLM_TYPE_14B; break; diff --git a/src/models/phimoe.cpp b/src/models/phimoe.cpp index 4575d6139cf5..c332553bc7d1 100644 --- a/src/models/phimoe.cpp +++ b/src/models/phimoe.cpp @@ -3,7 +3,7 @@ void llama_model_phimoe::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps); - switch (hparams.n_layer) { + switch (hparams.n_layer()) { case 32: type = LLM_TYPE_16x3_8B; break; default: type = LLM_TYPE_UNKNOWN; } diff --git a/src/models/plamo.cpp b/src/models/plamo.cpp index c7ed1211c311..246144519e43 100644 --- a/src/models/plamo.cpp +++ b/src/models/plamo.cpp @@ -3,7 +3,7 @@ void llama_model_plamo::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps); - switch (hparams.n_layer) { + switch (hparams.n_layer()) { case 40: type = LLM_TYPE_13B; break; default: type = LLM_TYPE_UNKNOWN; } diff --git a/src/models/plamo2.cpp b/src/models/plamo2.cpp index 2ffa0898f712..b93cf48bc5c6 100644 --- a/src/models/plamo2.cpp +++ b/src/models/plamo2.cpp @@ -11,11 +11,11 @@ void llama_model_plamo2::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_SSM_TIME_STEP_RANK, hparams.ssm_dt_rank); ml.get_key(LLM_KV_SSM_GROUP_COUNT, hparams.ssm_n_group); - for (uint32_t i = 0; i < hparams.n_layer; ++i) { + for (uint32_t i = 0; i < hparams.n_layer(); ++i) { hparams.is_recr_impl[i] = hparams.n_head_kv(i) == 0; } - switch (hparams.n_layer) { + switch (hparams.n_layer()) { case 16: type = LLM_TYPE_1B; break; case 32: if (hparams.n_embd == 2048) { diff --git a/src/models/plamo3.cpp b/src/models/plamo3.cpp index 29f3e803d685..16d0b1dcef71 100644 --- a/src/models/plamo3.cpp +++ b/src/models/plamo3.cpp @@ -13,7 +13,7 @@ void llama_model_plamo3::load_arch_hparams(llama_model_loader & ml) { hparams.swa_type = LLAMA_SWA_TYPE_NONE; } - switch (hparams.n_layer) { + switch (hparams.n_layer()) { case 24: type = LLM_TYPE_2B; break; default: type = LLM_TYPE_UNKNOWN; } diff --git a/src/models/plm.cpp b/src/models/plm.cpp index ce050919e6a8..8ca325f5e2cf 100644 --- a/src/models/plm.cpp +++ b/src/models/plm.cpp @@ -3,7 +3,8 @@ void llama_model_plm::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps); ml.get_key(LLM_KV_ATTENTION_KV_LORA_RANK, hparams.n_lora_kv); - switch (hparams.n_layer) { + + switch (hparams.n_layer()) { case 32: type = LLM_TYPE_1_8B; break; default: type = LLM_TYPE_UNKNOWN; } diff --git a/src/models/qwen.cpp b/src/models/qwen.cpp index 00467dbad7d5..1f5dff3843cf 100644 --- a/src/models/qwen.cpp +++ b/src/models/qwen.cpp @@ -3,7 +3,7 @@ void llama_model_qwen::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps); - switch (hparams.n_layer) { + switch (hparams.n_layer()) { case 32: type = LLM_TYPE_7B; break; case 40: type = LLM_TYPE_13B; break; default: type = LLM_TYPE_UNKNOWN; diff --git a/src/models/qwen2.cpp b/src/models/qwen2.cpp index a5147460bae6..e9c2ea80a6be 100644 --- a/src/models/qwen2.cpp +++ b/src/models/qwen2.cpp @@ -2,7 +2,8 @@ void llama_model_qwen2::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps); - switch (hparams.n_layer) { + + switch (hparams.n_layer()) { case 24: type = hparams.n_embd == 1024 ? LLM_TYPE_0_5B : LLM_TYPE_1B; break; case 28: type = hparams.n_embd == 1536 ? LLM_TYPE_1_5B : LLM_TYPE_7B; break; case 32: type = LLM_TYPE_7B; break; diff --git a/src/models/qwen2moe.cpp b/src/models/qwen2moe.cpp index 7cb03859debb..e831ed11aad6 100644 --- a/src/models/qwen2moe.cpp +++ b/src/models/qwen2moe.cpp @@ -5,7 +5,8 @@ void llama_model_qwen2moe::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_EXPERT_SHARED_FEED_FORWARD_LENGTH, hparams.n_ff_shexp, false); ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps); - switch (hparams.n_layer) { + + switch (hparams.n_layer()) { case 24: type = LLM_TYPE_A2_7B; break; case 28: type = LLM_TYPE_57B_A14B; break; default: type = LLM_TYPE_UNKNOWN; diff --git a/src/models/qwen3.cpp b/src/models/qwen3.cpp index 41b97fed9564..1d0d2fab362a 100644 --- a/src/models/qwen3.cpp +++ b/src/models/qwen3.cpp @@ -2,7 +2,8 @@ void llama_model_qwen3::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps); - switch (hparams.n_layer) { + + switch (hparams.n_layer()) { case 28: type = hparams.n_embd == 1024 ? LLM_TYPE_0_6B : LLM_TYPE_1_7B; break; case 36: type = hparams.n_embd == 2560 ? LLM_TYPE_4B : LLM_TYPE_8B; break; case 40: type = LLM_TYPE_14B; break; diff --git a/src/models/qwen35.cpp b/src/models/qwen35.cpp index 348650b37966..4b642cff467c 100644 --- a/src/models/qwen35.cpp +++ b/src/models/qwen35.cpp @@ -13,22 +13,20 @@ void llama_model_qwen35::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_SSM_GROUP_COUNT, hparams.ssm_n_group); // NextN/MTP (Qwen3.5/3.6): extra decoder block appended beyond the main stack - ml.get_key(LLM_KV_NEXTN_PREDICT_LAYERS, hparams.nextn_predict_layers, false); - GGML_ASSERT(hparams.nextn_predict_layers < hparams.n_layer && "nextn_predict_layers must be < n_layer"); + ml.get_key(LLM_KV_NEXTN_PREDICT_LAYERS, hparams.n_layer_nextn, false); + GGML_ASSERT(hparams.n_layer_nextn < hparams.n_layer_all && "n_layer_nextn must be < n_layer_impl"); // Mark recurrent layers (linear attention layers). MTP layers are dense // attention-only and must be flagged non-recurrent. - if (!ml.get_key_or_arr(LLM_KV_ATTENTION_RECURRENT_LAYERS, hparams.is_recr_impl, hparams.n_layer, false)) { - const uint32_t n_main = hparams.n_layer - hparams.nextn_predict_layers; - + if (!ml.get_key_or_arr(LLM_KV_ATTENTION_RECURRENT_LAYERS, hparams.is_recr_impl, hparams.n_layer_all, false)) { uint32_t full_attn_interval = 4; ml.get_key(LLM_KV_FULL_ATTENTION_INTERVAL, full_attn_interval, false); - for (uint32_t i = 0; i < hparams.n_layer; ++i) { - hparams.is_recr_impl[i] = (i < n_main) && ((i + 1) % full_attn_interval != 0); + for (uint32_t i = 0; i < hparams.n_layer_all; ++i) { + hparams.is_recr_impl[i] = (i < hparams.n_layer()) && ((i + 1) % full_attn_interval != 0); } } - switch (hparams.n_layer - hparams.nextn_predict_layers) { + switch (hparams.n_layer()) { case 24: type = hparams.n_embd == 1024 ? LLM_TYPE_0_8B : LLM_TYPE_2B; break; case 32: type = hparams.n_embd == 2560 ? LLM_TYPE_4B : LLM_TYPE_9B; break; case 64: type = LLM_TYPE_27B; break; @@ -39,9 +37,7 @@ void llama_model_qwen35::load_arch_hparams(llama_model_loader & ml) { void llama_model_qwen35::load_arch_tensors(llama_model_loader & ml) { LLAMA_LOAD_LOCALS; - const uint32_t n_main = n_layer - hparams.nextn_predict_layers; - const bool mtp_only = (hparams.nextn_predict_layers > 0) && - (ml.get_weight("blk.0.attn_norm.weight") == nullptr); + const bool mtp_only = (hparams.n_layer_nextn > 0) && (ml.get_weight("blk.0.attn_norm.weight") == nullptr); const int trunk_flags = mtp_only ? TENSOR_NOT_REQUIRED : 0; tok_embd = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD, "weight"), { n_embd, n_vocab }, 0); @@ -122,10 +118,10 @@ void llama_model_qwen35::load_arch_tensors(llama_model_loader & ml) { layer.nextn.shared_head_norm = create_tensor(tn(LLM_TENSOR_NEXTN_SHARED_HEAD_NORM, "weight", il), { n_embd }, TENSOR_NOT_REQUIRED); }; - for (int i = 0; i < (int) n_main; ++i) { + for (int i = 0; i < n_layer; ++i) { load_block_trunk(i, trunk_flags); } - for (int i = (int) n_main; i < n_layer; ++i) { + for (int i = n_layer; i < n_layer_all; ++i) { load_block_mtp(i); } } @@ -159,8 +155,7 @@ llama_model_qwen35::graph::graph(const llama_model & model, const llm_graph_para ggml_tensor * inp_out_ids = build_inp_out_ids(); // MTP/NextN layers are loaded as extra decoder blocks but not executed in the main pass. - const int n_transformer_layers = n_layer - (int) hparams.nextn_predict_layers; - for (int il = 0; il < n_transformer_layers; ++il) { + for (int il = 0; il < n_layer; ++il) { ggml_tensor * inpSA = inpL; cur = build_norm(inpL, model.layers[il].attn_norm, nullptr, LLM_NORM_RMS, il); @@ -177,7 +172,7 @@ llama_model_qwen35::graph::graph(const llama_model & model, const llm_graph_para cur = build_layer_attn(inp->get_attn(), cur, inp_pos, sections, il); } - if (il == n_transformer_layers - 1 && inp_out_ids && cparams.embeddings_nextn_masked) { + if (il == n_layer - 1 && inp_out_ids && cparams.embeddings_nextn_masked) { cur = ggml_get_rows(ctx0, cur, inp_out_ids); inpSA = ggml_get_rows(ctx0, inpSA, inp_out_ids); } @@ -490,15 +485,15 @@ ggml_tensor * llama_model_qwen35::graph::build_layer_ffn(ggml_tensor * cur, cons // LLM_GRAPH_TYPE_DECODER_MTP draft head for Qwen3.5/3.6 dense series llama_model_qwen35::graph_mtp::graph_mtp(const llama_model & model, const llm_graph_params & params) : llm_graph_context(params) { - GGML_ASSERT(hparams.nextn_predict_layers > 0 && "QWEN35 MTP requires nextn_predict_layers > 0"); - GGML_ASSERT(hparams.nextn_predict_layers == 1 && "QWEN35 MTP currently only supports a single MTP block"); + GGML_ASSERT(hparams.n_layer_nextn > 0 && "QWEN35 MTP requires n_layer_nextn > 0"); + GGML_ASSERT(hparams.n_layer_nextn == 1 && "QWEN35 MTP currently only supports a single MTP block"); const int64_t n_embd_head = hparams.n_embd_head_v(); GGML_ASSERT(n_embd_head == hparams.n_embd_head_k()); // hparams.n_layer includes both main model layers and MTP layers. The MTP // layer is stored immediately after the main layers in model.layers[]. - const int il = (int) hparams.n_layer - (int) hparams.nextn_predict_layers; + const int il = hparams.n_layer(); const auto & layer = model.layers[il]; GGML_ASSERT(layer.nextn.eh_proj && "MTP block missing nextn.eh_proj"); diff --git a/src/models/qwen35moe.cpp b/src/models/qwen35moe.cpp index 7d906191cbbc..eb5e9a406a15 100644 --- a/src/models/qwen35moe.cpp +++ b/src/models/qwen35moe.cpp @@ -16,22 +16,20 @@ void llama_model_qwen35moe::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_SSM_GROUP_COUNT, hparams.ssm_n_group); // NextN/MTP (Qwen3.5/3.6): extra decoder block appended beyond the main stack - ml.get_key(LLM_KV_NEXTN_PREDICT_LAYERS, hparams.nextn_predict_layers, false); - GGML_ASSERT(hparams.nextn_predict_layers < hparams.n_layer && "nextn_predict_layers must be < n_layer"); + ml.get_key(LLM_KV_NEXTN_PREDICT_LAYERS, hparams.n_layer_nextn, false); + GGML_ASSERT(hparams.n_layer_nextn < hparams.n_layer_all && "n_layer_nextn must be < n_layer_impl"); // Mark recurrent layers (linear attention layers). MTP layers are dense // attention-only and must be flagged non-recurrent. - if (!ml.get_key_or_arr(LLM_KV_ATTENTION_RECURRENT_LAYERS, hparams.is_recr_impl, hparams.n_layer, false)) { - const uint32_t n_main = hparams.n_layer - hparams.nextn_predict_layers; - + if (!ml.get_key_or_arr(LLM_KV_ATTENTION_RECURRENT_LAYERS, hparams.is_recr_impl, hparams.n_layer_all, false)) { uint32_t full_attn_interval = 4; ml.get_key(LLM_KV_FULL_ATTENTION_INTERVAL, full_attn_interval, false); - for (uint32_t i = 0; i < hparams.n_layer; ++i) { - hparams.is_recr_impl[i] = (i < n_main) && ((i + 1) % full_attn_interval != 0); + for (uint32_t i = 0; i < hparams.n_layer_all; ++i) { + hparams.is_recr_impl[i] = (i < hparams.n_layer()) && ((i + 1) % full_attn_interval != 0); } } - switch (hparams.n_layer - hparams.nextn_predict_layers) { + switch (hparams.n_layer()) { case 40: type = LLM_TYPE_35B_A3B; break; case 48: type = LLM_TYPE_122B_A10B; break; case 60: type = LLM_TYPE_397B_A17B; break; @@ -42,9 +40,7 @@ void llama_model_qwen35moe::load_arch_hparams(llama_model_loader & ml) { void llama_model_qwen35moe::load_arch_tensors(llama_model_loader & ml) { LLAMA_LOAD_LOCALS; - const uint32_t n_main = n_layer - hparams.nextn_predict_layers; - const bool mtp_only = (hparams.nextn_predict_layers > 0) && - (ml.get_weight("blk.0.attn_norm.weight") == nullptr); + const bool mtp_only = (hparams.n_layer_nextn > 0) && (ml.get_weight("blk.0.attn_norm.weight") == nullptr); const int trunk_flags = mtp_only ? TENSOR_NOT_REQUIRED : 0; tok_embd = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD, "weight"), { n_embd, n_vocab }, 0); @@ -145,10 +141,10 @@ void llama_model_qwen35moe::load_arch_tensors(llama_model_loader & ml) { layer.nextn.shared_head_norm = create_tensor(tn(LLM_TENSOR_NEXTN_SHARED_HEAD_NORM, "weight", il), { n_embd }, TENSOR_NOT_REQUIRED); }; - for (int i = 0; i < (int) n_main; ++i) { + for (int i = 0; i < n_layer; ++i) { load_block_trunk(i, trunk_flags); } - for (int i = (int) n_main; i < n_layer; ++i) { + for (int i = n_layer; i < n_layer_all; ++i) { load_block_mtp(i); } } @@ -182,8 +178,7 @@ llama_model_qwen35moe::graph::graph(const llama_model & model, const llm_graph_p ggml_tensor * inp_out_ids = build_inp_out_ids(); // MTP/NextN layers are loaded as extra decoder blocks but not executed in the main pass. - const int n_transformer_layers = n_layer - (int) hparams.nextn_predict_layers; - for (int il = 0; il < n_transformer_layers; ++il) { + for (int il = 0; il < n_layer; ++il) { ggml_tensor * inpSA = inpL; cur = build_norm(inpL, model.layers[il].attn_norm, nullptr, LLM_NORM_RMS, il); @@ -200,7 +195,7 @@ llama_model_qwen35moe::graph::graph(const llama_model & model, const llm_graph_p cur = build_layer_attn(inp->get_attn(), cur, inp_pos, sections, il); } - if (il == n_transformer_layers - 1 && inp_out_ids && cparams.embeddings_nextn_masked) { + if (il == n_layer - 1 && inp_out_ids && cparams.embeddings_nextn_masked) { cur = ggml_get_rows(ctx0, cur, inp_out_ids); inpSA = ggml_get_rows(ctx0, inpSA, inp_out_ids); } @@ -555,13 +550,13 @@ ggml_tensor * llama_model_qwen35moe::graph::build_layer_ffn(ggml_tensor * cur, c // LLM_GRAPH_TYPE_DECODER_MTP draft head for Qwen3.5/3.6 MoE llama_model_qwen35moe::graph_mtp::graph_mtp(const llama_model & model, const llm_graph_params & params) : llm_graph_context(params) { - GGML_ASSERT(hparams.nextn_predict_layers > 0 && "QWEN35MOE MTP requires nextn_predict_layers > 0"); - GGML_ASSERT(hparams.nextn_predict_layers == 1 && "QWEN35MOE MTP currently only supports a single MTP block"); + GGML_ASSERT(hparams.n_layer_nextn > 0 && "QWEN35MOE MTP requires n_layer_nextn > 0"); + GGML_ASSERT(hparams.n_layer_nextn == 1 && "QWEN35MOE MTP currently only supports a single MTP block"); const int64_t n_embd_head = hparams.n_embd_head_v(); GGML_ASSERT(n_embd_head == hparams.n_embd_head_k()); - const int il = (int) hparams.n_layer - (int) hparams.nextn_predict_layers; + const int il = hparams.n_layer(); const auto & layer = model.layers[il]; GGML_ASSERT(layer.nextn.eh_proj && "MTP block missing nextn.eh_proj"); diff --git a/src/models/qwen3moe.cpp b/src/models/qwen3moe.cpp index a4f8e1379c90..317e668bec79 100644 --- a/src/models/qwen3moe.cpp +++ b/src/models/qwen3moe.cpp @@ -1,10 +1,10 @@ #include "models.h" void llama_model_qwen3moe::load_arch_hparams(llama_model_loader & ml) { - ml.get_key(LLM_KV_EXPERT_FEED_FORWARD_LENGTH, hparams.n_ff_exp, false); - + ml.get_key(LLM_KV_EXPERT_FEED_FORWARD_LENGTH, hparams.n_ff_exp, false); ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps); - switch (hparams.n_layer) { + + switch (hparams.n_layer()) { case 48: type = LLM_TYPE_30B_A3B; break; case 94: type = LLM_TYPE_235B_A22B; break; default: type = LLM_TYPE_UNKNOWN; diff --git a/src/models/qwen3next.cpp b/src/models/qwen3next.cpp index 9e09ae6f232d..97200a44072f 100644 --- a/src/models/qwen3next.cpp +++ b/src/models/qwen3next.cpp @@ -14,15 +14,15 @@ void llama_model_qwen3next::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_SSM_GROUP_COUNT, hparams.ssm_n_group); // Mark recurrent layers (linear attention layers) - if (!ml.get_key_or_arr(LLM_KV_ATTENTION_RECURRENT_LAYERS, hparams.is_recr_impl, hparams.n_layer, false)) { + if (!ml.get_key_or_arr(LLM_KV_ATTENTION_RECURRENT_LAYERS, hparams.is_recr_impl, hparams.n_layer_all, false)) { uint32_t full_attn_interval = 4; ml.get_key(LLM_KV_FULL_ATTENTION_INTERVAL, full_attn_interval, false); - for (uint32_t i = 0; i < hparams.n_layer; ++i) { - hparams.is_recr_impl[i] = ((i + 1) % full_attn_interval != 0); + for (uint32_t i = 0; i < hparams.n_layer_all; ++i) { + hparams.is_recr_impl[i] = (i < hparams.n_layer()) && ((i + 1) % full_attn_interval != 0); } } - switch (hparams.n_layer) { + switch (hparams.n_layer()) { case 48: type = LLM_TYPE_80B_A3B; break; default: type = LLM_TYPE_UNKNOWN; } diff --git a/src/models/qwen3vl.cpp b/src/models/qwen3vl.cpp index 5defd8939448..724d6140d193 100644 --- a/src/models/qwen3vl.cpp +++ b/src/models/qwen3vl.cpp @@ -4,7 +4,8 @@ void llama_model_qwen3vl::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_NUM_DEEPSTACK_LAYERS, hparams.n_deepstack_layers, false); ml.get_key_or_arr(LLM_KV_ROPE_DIMENSION_SECTIONS, hparams.rope_sections, 4, true); ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps); - switch (hparams.n_layer) { + + switch (hparams.n_layer()) { case 28: type = LLM_TYPE_1_7B; break; case 36: type = hparams.n_embd == 2560 ? LLM_TYPE_4B : LLM_TYPE_8B; break; case 64: type = LLM_TYPE_32B; break; diff --git a/src/models/qwen3vlmoe.cpp b/src/models/qwen3vlmoe.cpp index 5b77df57122e..7c41592f7727 100644 --- a/src/models/qwen3vlmoe.cpp +++ b/src/models/qwen3vlmoe.cpp @@ -5,7 +5,8 @@ void llama_model_qwen3vlmoe::load_arch_hparams(llama_model_loader & ml) { ml.get_key_or_arr(LLM_KV_ROPE_DIMENSION_SECTIONS, hparams.rope_sections, 4, true); ml.get_key(LLM_KV_EXPERT_FEED_FORWARD_LENGTH, hparams.n_ff_exp, false); ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps); - switch (hparams.n_layer) { + + switch (hparams.n_layer()) { case 48: type = LLM_TYPE_30B_A3B; break; case 94: type = LLM_TYPE_235B_A22B; break; default: type = LLM_TYPE_UNKNOWN; diff --git a/src/models/refact.cpp b/src/models/refact.cpp index bf3949a90920..a46c358fa68a 100644 --- a/src/models/refact.cpp +++ b/src/models/refact.cpp @@ -2,7 +2,8 @@ void llama_model_refact::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps); - switch (hparams.n_layer) { + + switch (hparams.n_layer()) { case 32: type = LLM_TYPE_1B; break; default: type = LLM_TYPE_UNKNOWN; } diff --git a/src/models/rnd1.cpp b/src/models/rnd1.cpp index ca8e009615e9..fc276ce591bf 100644 --- a/src/models/rnd1.cpp +++ b/src/models/rnd1.cpp @@ -2,12 +2,13 @@ void llama_model_rnd1::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_EXPERT_FEED_FORWARD_LENGTH, hparams.n_ff_exp, false); - ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps); - switch (hparams.n_layer) { + + switch (hparams.n_layer()) { case 48: type = LLM_TYPE_30B_A3B; break; default: type = LLM_TYPE_UNKNOWN; } + // Set non-causal attention for diffusion models hparams.causal_attn = false; } diff --git a/src/models/rwkv6.cpp b/src/models/rwkv6.cpp index ba2a9dfa0db4..0b5013dc7585 100644 --- a/src/models/rwkv6.cpp +++ b/src/models/rwkv6.cpp @@ -9,7 +9,7 @@ void llama_model_rwkv6::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_RESCALE_EVERY_N_LAYERS, hparams.rescale_every_n_layers, false); ml.get_key(LLM_KV_TOKEN_SHIFT_COUNT, hparams.token_shift_count, false); - switch (hparams.n_layer) { + switch (hparams.n_layer()) { case 24: type = LLM_TYPE_1_6B; break; case 32: switch (hparams.n_embd) { diff --git a/src/models/rwkv6qwen2.cpp b/src/models/rwkv6qwen2.cpp index 566b8cdcb549..6c7db514435e 100644 --- a/src/models/rwkv6qwen2.cpp +++ b/src/models/rwkv6qwen2.cpp @@ -9,7 +9,7 @@ void llama_model_rwkv6qwen2::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_RESCALE_EVERY_N_LAYERS, hparams.rescale_every_n_layers, false); ml.get_key(LLM_KV_TOKEN_SHIFT_COUNT, hparams.token_shift_count, false); - switch (hparams.n_layer) { + switch (hparams.n_layer()) { case 24: type = LLM_TYPE_1_6B; break; case 32: switch (hparams.n_embd) { diff --git a/src/models/rwkv7.cpp b/src/models/rwkv7.cpp index 7574b252621c..67c51f5b59c6 100644 --- a/src/models/rwkv7.cpp +++ b/src/models/rwkv7.cpp @@ -10,7 +10,7 @@ void llama_model_rwkv7::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_ATTENTION_GATE_LORA_RANK, hparams.n_lora_gate, false); ml.get_key(LLM_KV_TOKEN_SHIFT_COUNT, hparams.token_shift_count, false); - switch (hparams.n_layer) { + switch (hparams.n_layer()) { case 12: switch (hparams.n_embd) { case 768: type = LLM_TYPE_190M; break; diff --git a/src/models/seed-oss.cpp b/src/models/seed-oss.cpp index 806cba574be8..57de881a091f 100644 --- a/src/models/seed-oss.cpp +++ b/src/models/seed-oss.cpp @@ -2,7 +2,8 @@ void llama_model_seed_oss::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps); - switch (hparams.n_layer) { + + switch (hparams.n_layer()) { case 64: type = LLM_TYPE_36B; break; default: type = LLM_TYPE_UNKNOWN; } diff --git a/src/models/smallthinker.cpp b/src/models/smallthinker.cpp index 4231cccc666f..a8e3d957f1f0 100644 --- a/src/models/smallthinker.cpp +++ b/src/models/smallthinker.cpp @@ -15,14 +15,14 @@ void llama_model_smallthinker::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_ROPE_FREQ_BASE_SWA, hparams.rope_freq_base_train_swa, false); } else { hparams.swa_type = LLAMA_SWA_TYPE_NONE; - hparams.n_no_rope_layer_step = hparams.n_layer; + hparams.n_no_rope_layer_step = hparams.n_layer(); } ml.get_key(LLM_KV_EXPERT_FEED_FORWARD_LENGTH, hparams.n_ff_exp, false); ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps); ml.get_key(LLM_KV_EXPERT_GATING_FUNC, hparams.expert_gating_func, false); - switch (hparams.n_layer) { + switch (hparams.n_layer()) { case 32: type = LLM_TYPE_4B; break; case 52: type = LLM_TYPE_20B; break; default: type = LLM_TYPE_UNKNOWN; diff --git a/src/models/smollm3.cpp b/src/models/smollm3.cpp index 90e7d473eaff..c67d967b2040 100644 --- a/src/models/smollm3.cpp +++ b/src/models/smollm3.cpp @@ -4,7 +4,7 @@ void llama_model_smollm3::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps); hparams.n_no_rope_layer_step = 4; - switch (hparams.n_layer) { + switch (hparams.n_layer()) { case 36: type = LLM_TYPE_3B; break; default: type = LLM_TYPE_UNKNOWN; } diff --git a/src/models/stablelm.cpp b/src/models/stablelm.cpp index 4da7f7aefcf0..bf6087b87960 100644 --- a/src/models/stablelm.cpp +++ b/src/models/stablelm.cpp @@ -3,7 +3,7 @@ void llama_model_stablelm::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_ATTENTION_LAYERNORM_EPS, hparams.f_norm_eps); - switch (hparams.n_layer) { + switch (hparams.n_layer()) { case 24: type = LLM_TYPE_1B; break; case 32: type = LLM_TYPE_3B; break; case 40: type = LLM_TYPE_12B; break; diff --git a/src/models/starcoder.cpp b/src/models/starcoder.cpp index e131af058bc3..f73a88fd4e90 100644 --- a/src/models/starcoder.cpp +++ b/src/models/starcoder.cpp @@ -2,7 +2,8 @@ void llama_model_starcoder::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_ATTENTION_LAYERNORM_EPS, hparams.f_norm_eps); - switch (hparams.n_layer) { + + switch (hparams.n_layer()) { case 24: type = LLM_TYPE_1B; break; case 36: type = LLM_TYPE_3B; break; case 42: type = LLM_TYPE_7B; break; diff --git a/src/models/starcoder2.cpp b/src/models/starcoder2.cpp index 9c207c028856..b81b469374a4 100644 --- a/src/models/starcoder2.cpp +++ b/src/models/starcoder2.cpp @@ -2,7 +2,8 @@ void llama_model_starcoder2::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_ATTENTION_LAYERNORM_EPS, hparams.f_norm_eps); - switch (hparams.n_layer) { + + switch (hparams.n_layer()) { case 30: type = LLM_TYPE_3B; break; case 32: type = LLM_TYPE_7B; break; case 40: type = LLM_TYPE_15B; break; diff --git a/src/models/step35.cpp b/src/models/step35.cpp index cf9942b200f7..e2218c587044 100644 --- a/src/models/step35.cpp +++ b/src/models/step35.cpp @@ -23,16 +23,16 @@ void llama_model_step35::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_ATTENTION_SLIDING_WINDOW, hparams.n_swa); ml.get_key(LLM_KV_ROPE_FREQ_BASE_SWA, hparams.rope_freq_base_train_swa, false); - ml.get_key_or_arr(LLM_KV_ATTENTION_SLIDING_WINDOW_PATTERN, hparams.is_swa_impl, hparams.n_layer); + ml.get_key_or_arr(LLM_KV_ATTENTION_SLIDING_WINDOW_PATTERN, hparams.is_swa_impl, hparams.n_layer()); - ml.get_key_or_arr(LLM_KV_SWIGLU_CLAMP_EXP, hparams.swiglu_clamp_exp, hparams.n_layer, false); - ml.get_key_or_arr(LLM_KV_SWIGLU_CLAMP_SHEXP, hparams.swiglu_clamp_shexp, hparams.n_layer, false); + ml.get_key_or_arr(LLM_KV_SWIGLU_CLAMP_EXP, hparams.swiglu_clamp_exp, hparams.n_layer(), false); + ml.get_key_or_arr(LLM_KV_SWIGLU_CLAMP_SHEXP, hparams.swiglu_clamp_shexp, hparams.n_layer(), false); // NextN/MTP (Step3p5): extra decoder block appended beyond the main stack. - ml.get_key(LLM_KV_NEXTN_PREDICT_LAYERS, hparams.nextn_predict_layers, false); - GGML_ASSERT(hparams.nextn_predict_layers < hparams.n_layer && "nextn_predict_layers must be < n_layer"); + ml.get_key(LLM_KV_NEXTN_PREDICT_LAYERS, hparams.n_layer_nextn, false); + GGML_ASSERT(hparams.n_layer_nextn < hparams.n_layer_all && "n_layer_nextn must be < n_layer_impl"); - switch (hparams.n_layer - hparams.nextn_predict_layers) { + switch (hparams.n_layer()) { case 45: type = LLM_TYPE_196B_A11B; break; default: type = LLM_TYPE_UNKNOWN; } @@ -41,15 +41,12 @@ void llama_model_step35::load_arch_hparams(llama_model_loader & ml) { void llama_model_step35::load_arch_tensors(llama_model_loader & ml) { LLAMA_LOAD_LOCALS; - const uint32_t n_main = n_layer - hparams.nextn_predict_layers; - const bool mtp_only = (hparams.nextn_predict_layers > 0) && - (ml.get_weight("blk.0.attn_norm.weight") == nullptr); + const bool mtp_only = (hparams.n_layer_nextn > 0) && (ml.get_weight("blk.0.attn_norm.weight") == nullptr); // Trunk-only: the GGUF declares MTP layers in metadata but the actual MTP // tensors live in a separate file (e.g. user split target/draft). Mark // MTP tensors NOT_REQUIRED so the trunk loads cleanly. - const std::string mtp_probe = "blk." + std::to_string(n_main) + ".nextn.eh_proj.weight"; - const bool trunk_only = (hparams.nextn_predict_layers > 0) && - (ml.get_weight(mtp_probe.c_str()) == nullptr); + const std::string mtp_probe = "blk." + std::to_string(n_layer) + ".nextn.eh_proj.weight"; + const bool trunk_only = (hparams.n_layer_nextn > 0) && (ml.get_weight(mtp_probe.c_str()) == nullptr); const int trunk_flags = mtp_only ? TENSOR_NOT_REQUIRED : 0; const int mtp_flags = trunk_only ? TENSOR_NOT_REQUIRED : 0; @@ -176,7 +173,7 @@ void llama_model_step35::load_arch_tensors(llama_model_loader & ml) { layer.nextn.shared_head_norm = create_tensor(tn(LLM_TENSOR_NEXTN_SHARED_HEAD_NORM, "weight", i), { n_embd }, TENSOR_NOT_REQUIRED); }; - for (int i = 0; i < (int) n_main; ++i) { + for (int i = 0; i < n_layer; ++i) { load_block_trunk(i, trunk_flags); } // Only the first MTP block (i == n_main) is required at runtime — the @@ -184,8 +181,8 @@ void llama_model_step35::load_arch_tensors(llama_model_loader & ml) { // Trailing MTP blocks are loaded if present (so an un-pruned GGUF with // all MTP layers still works) but tolerated when absent via the pruning // path. See scripts/prune_step35_extra_mtp.py for the pruner. - for (int i = (int) n_main; i < n_layer; ++i) { - load_block_mtp(i, /*is_first_mtp=*/ i == (int) n_main); + for (int i = n_layer; i < n_layer_all; ++i) { + load_block_mtp(i, /*is_first_mtp=*/ i == n_layer); } } @@ -206,8 +203,7 @@ llama_model_step35::graph::graph(const llama_model & model, const llm_graph_para ggml_tensor * inp_out_ids = build_inp_out_ids(); // MTP/NextN layers are loaded as extra decoder blocks but not executed in the main pass. - const int n_transformer_layers = n_layer - (int) hparams.nextn_predict_layers; - for (int il = 0; il < n_transformer_layers; ++il) { + for (int il = 0; il < n_layer; ++il) { ggml_tensor * inpSA = inpL; const uint32_t n_head_l = hparams.n_head(il); @@ -294,7 +290,7 @@ llama_model_step35::graph::graph(const llama_model & model, const llm_graph_para cb(cur, "attn_proj", il); } - if (il == n_transformer_layers - 1 && inp_out_ids && cparams.embeddings_nextn_masked) { + if (il == n_layer - 1 && inp_out_ids && cparams.embeddings_nextn_masked) { cur = ggml_get_rows(ctx0, cur, inp_out_ids); inpSA = ggml_get_rows(ctx0, inpSA, inp_out_ids); } @@ -374,7 +370,7 @@ llama_model_step35::graph::graph(const llama_model & model, const llm_graph_para // LLM_GRAPH_TYPE_DECODER_MTP draft head for Step3p5 (MoE) llama_model_step35::graph_mtp::graph_mtp(const llama_model & model, const llm_graph_params & params) : llm_graph_context(params) { - GGML_ASSERT(hparams.nextn_predict_layers > 0 && "STEP35 MTP requires nextn_predict_layers > 0"); + GGML_ASSERT(hparams.n_layer_nextn > 0 && "STEP35 MTP requires n_layer_nextn > 0"); // Single-block MTP only: always run the first trained MTP block (Qwen // MTP / vLLM single-MTP-layer style). Multi-block round-robin proved to @@ -382,7 +378,7 @@ llama_model_step35::graph_mtp::graph_mtp(const llama_model & model, const llm_gr // blocks are loaded with TENSOR_NOT_REQUIRED so pruned GGUFs (with just // block 0) also work — see load_arch_tensors below and // scripts/prune_step35_extra_mtp.py. - const int il = (int) hparams.n_layer - (int) hparams.nextn_predict_layers; + const int il = hparams.n_layer(); const auto & layer = model.layers[il]; GGML_ASSERT(layer.nextn.eh_proj && "MTP block missing nextn.eh_proj"); diff --git a/src/models/t5.cpp b/src/models/t5.cpp index 73e327414066..b0e3f062572f 100644 --- a/src/models/t5.cpp +++ b/src/models/t5.cpp @@ -9,10 +9,10 @@ void llama_model_t5::load_arch_hparams(llama_model_loader & ml) { hparams.dec_start_token_id = dec_start_token_id; } - hparams.dec_n_layer = hparams.n_layer; + hparams.dec_n_layer = hparams.n_layer(); ml.get_key(LLM_KV_DECODER_BLOCK_COUNT, hparams.dec_n_layer, false); - switch (hparams.n_layer) { + switch (hparams.n_layer()) { case 6: type = LLM_TYPE_60M; break; // t5-small case 8: type = LLM_TYPE_80M; break; // flan-t5-small case 12: diff --git a/src/models/talkie.cpp b/src/models/talkie.cpp index 1258eeb19b67..393e8f65bf4d 100644 --- a/src/models/talkie.cpp +++ b/src/models/talkie.cpp @@ -4,7 +4,7 @@ void llama_model_talkie::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps); ml.get_key(LLM_KV_LOGIT_SCALE, hparams.f_logit_scale); - switch (hparams.n_layer) { + switch (hparams.n_layer()) { case 40: type = LLM_TYPE_13B; break; default: type = LLM_TYPE_UNKNOWN; } diff --git a/src/models/xverse.cpp b/src/models/xverse.cpp index d6d1c7a2e5de..3135001293a8 100644 --- a/src/models/xverse.cpp +++ b/src/models/xverse.cpp @@ -2,7 +2,8 @@ void llama_model_xverse::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps); - switch (hparams.n_layer) { + + switch (hparams.n_layer()) { case 32: type = LLM_TYPE_7B; break; case 40: type = LLM_TYPE_13B; break; case 80: type = LLM_TYPE_65B; break; diff --git a/tests/test-llama-archs.cpp b/tests/test-llama-archs.cpp index 4fe585e29a22..8037a11398b0 100644 --- a/tests/test-llama-archs.cpp +++ b/tests/test-llama-archs.cpp @@ -392,7 +392,7 @@ static bool arch_supported(const llm_arch arch) { if (arch == LLM_ARCH_WAVTOKENIZER_DEC) { return false; // FIXME CUDA backend crashes. } - if (arch == LLM_ARCH_GEMMA4) { + if (arch == LLM_ARCH_GEMMA4 || arch == LLM_ARCH_GEMMA4_ASSISTANT) { return false; // FIXME @ngxson } if (arch == LLM_ARCH_LLAMA_EMBED || arch == LLM_ARCH_GEMMA_EMBEDDING || arch == LLM_ARCH_T5ENCODER) { @@ -447,7 +447,7 @@ static int save_models(const llm_arch target_arch, const size_t seed, const ggml if (target_arch != LLM_ARCH_UNKNOWN && arch != target_arch) { continue; } - if (arch == LLM_ARCH_GEMMA4) { + if (arch == LLM_ARCH_GEMMA4 || arch == LLM_ARCH_GEMMA4_ASSISTANT) { continue; // FIXME: ISWA KV cache initialization needs more fixture params } for (bool moe : {false, true}) { @@ -550,7 +550,7 @@ static int test_backends(const llm_arch target_arch, const size_t seed, const gg if (target_arch != LLM_ARCH_UNKNOWN && arch != target_arch) { continue; } - if (arch == LLM_ARCH_GEMMA4) { + if (arch == LLM_ARCH_GEMMA4 || arch == LLM_ARCH_GEMMA4_ASSISTANT) { continue; // FIXME: ISWA KV cache initialization needs more fixture params } diff --git a/tools/imatrix/imatrix.cpp b/tools/imatrix/imatrix.cpp index 3f7f3a11dfa3..3431a4eca84b 100644 --- a/tools/imatrix/imatrix.cpp +++ b/tools/imatrix/imatrix.cpp @@ -1,5 +1,6 @@ #include "arg.h" #include "common.h" +#include "imatrix-loader.h" #include "log.h" #include "llama.h" #include "gguf.h" @@ -34,10 +35,6 @@ static void print_usage(int, char ** argv) { LOG("\n"); } -static const char * const LLM_KV_IMATRIX_DATASETS = "imatrix.datasets"; -static const char * const LLM_KV_IMATRIX_CHUNK_COUNT = "imatrix.chunk_count"; -static const char * const LLM_KV_IMATRIX_CHUNK_SIZE = "imatrix.chunk_size"; - struct Stats { std::vector values; std::vector counts; @@ -65,7 +62,6 @@ class IMatrixCollector { bool collect_imatrix(struct ggml_tensor * t, bool ask, void * user_data); void save_imatrix_legacy(int32_t ncall = -1) const; void save_imatrix(int32_t n_chunk = -1) const; - bool load_imatrix_legacy(const char * fname); bool load_imatrix(const char * file_name); const std::unordered_map & get_mstats() const { return m_stats; } private: @@ -624,204 +620,63 @@ void IMatrixCollector::save_imatrix(int32_t n_chunk) const { ggml_free(ctx); } -bool IMatrixCollector::load_imatrix_legacy(const char * fname) { - std::ifstream in(fname, std::ios::binary); - if (!in) { - LOG_ERR("%s: failed to open %s\n", __func__, fname); - return false; - } - int n_entries; - in.read((char *) &n_entries, sizeof(n_entries)); - if (in.fail() || n_entries < 1) { - LOG_ERR("%s: no data in file %s\n", __func__, fname); +bool IMatrixCollector::load_imatrix(const char * file_name) { + common_imatrix loaded; + if (!common_imatrix_load(file_name, loaded)) { return false; } - // Guess the chunk size because it's not stored in the file - const int32_t chunk_size = m_params.n_ctx / m_params.n_parallel; - - for (int i = 0; i < n_entries; ++i) { - int32_t len = 0; - in.read((char *) &len, sizeof(len)); - std::vector name_as_vec(len + 1); - in.read((char *) name_as_vec.data(), len); - if (in.fail()) { - LOG_ERR("%s: failed reading name for entry %d from %s\n", __func__, i + 1, fname); - return false; - } - name_as_vec[len] = 0; - std::string name{ name_as_vec.data() }; - auto & e = m_stats[std::move(name)]; - int32_t ncall = 0; - in.read((char *) &ncall, sizeof(ncall)); - int32_t nval = 0; - in.read((char *) &nval, sizeof(nval)); - if (in.fail() || nval < 1) { - LOG_ERR("%s: failed reading number of values for entry %d\n", __func__, i); - m_stats = {}; - return false; - } - if (e.values.empty()) { - e.values.resize(nval, 0.0f); - e.counts.resize(1, 0); - } - - std::vector tmp(nval); - in.read((char *) tmp.data(), nval * sizeof(float)); - if (in.fail()) { - LOG_ERR("%s: failed reading data for entry %d\n", __func__, i); - m_stats = {}; - return false; - } + const int32_t chunk_size = m_params.n_ctx / m_params.n_parallel; + const bool is_legacy = loaded.is_legacy; - // Recreate the state as expected by save_imatrix(), and correct for weighted sum. - for (int i = 0; i < nval; i++) { - e.values[i] += tmp[i] * chunk_size; - } - // The legacy format doesn't distinguish the counts for different experts - for (size_t j = 0; j < e.counts.size(); ++j) { - e.counts[j] += ncall * chunk_size; - } - } + for (auto & [name, entry] : loaded.entries) { + auto & e = m_stats[name]; - { - // TODO: extract into its own method; this is also used by the GGUF-based format - // Calculate the last chunk count - int64_t max_count = 0; - for (const auto & stats : m_stats) { - for (int64_t count : stats.second.counts) { - if (count > max_count) { - max_count = count; - } + if (is_legacy) { + // Legacy format: sums contain (raw_sum/raw_count)*ncall, counts contain {ncall} + // Reconstruct raw form by multiplying by chunk_size + if (e.values.empty()) { + e.values.resize(entry.sums.size(), 0.0f); + e.counts.resize(1, 0); } - } - m_last_chunk = max_count / (chunk_size); - } - - { - // Read the number of calls the matrix was computed with - int32_t n_calls; - in.read((char *) &n_calls, sizeof(n_calls)); - // ignore it because it's not important - } - - // Read the dataset path to include it when writing to GGUF - if (!in.fail()){ - int32_t len = 0; - in.read((char *) &len, sizeof(len)); - if (!in.fail()) { - std::vector dataset; - dataset.resize(len + 1, 0); - in.read(dataset.data(), len); - if (!in.fail()) { - m_datasets.push_back(dataset.data()); + for (size_t j = 0; j < entry.sums.size(); ++j) { + e.values[j] += entry.sums[j] * chunk_size; + } + for (size_t j = 0; j < e.counts.size(); ++j) { + e.counts[j] += entry.counts[0] * chunk_size; } - } - } - - return true; -} - -// Using GGUF as the file format, for greater extensibility -bool IMatrixCollector::load_imatrix(const char * file_name) { - struct ggml_context * ctx = nullptr; - struct gguf_init_params meta_gguf_params = { - /* .no_alloc = */ false, // the data is needed - /* .ctx = */ &ctx, - }; - struct gguf_context * ctx_gguf = gguf_init_from_file(file_name, meta_gguf_params); - if (!ctx_gguf) { - return this->load_imatrix_legacy(file_name); - } - const int32_t n_entries = gguf_get_n_tensors(ctx_gguf); - if (n_entries < 1) { - LOG_ERR("%s: no data in file %s\n", __func__, file_name); - gguf_free(ctx_gguf); - ggml_free(ctx); - return false; - } - - const int64_t datasets_key = gguf_find_key(ctx_gguf, LLM_KV_IMATRIX_DATASETS); - if (datasets_key != -1 && gguf_get_arr_type(ctx_gguf, datasets_key) == GGUF_TYPE_STRING) { - const int64_t n = gguf_get_arr_n(ctx_gguf, datasets_key); - m_datasets.reserve(m_datasets.size() + n); - for (int64_t i = 0; i < n; ++i) { - m_datasets.push_back(gguf_get_arr_str(ctx_gguf, datasets_key, i)); - } - } - - const std::string in_sum2_suffix{ ".in_sum2" }; - const std::string counts_suffix{ ".counts" }; - - // Could re-use m_stats instead, but this allows - // checking for completeness of *each* loaded imatrix file - // and also makes it easier to re-use a similar implementation in quantize.cpp - // Using an ordered map to get a deterministic iteration order. - std::map> sums_counts_for; - - for (struct ggml_tensor * cur = ggml_get_first_tensor(ctx); cur; cur = ggml_get_next_tensor(ctx, cur)) { - std::string name = cur->name; - - if (name.empty()) { continue; } - - if (string_remove_suffix(name, in_sum2_suffix)) { - // in_sum2 - sums_counts_for[std::move(name)].first = cur; - } else if (string_remove_suffix(name, counts_suffix)) { - // counts - sums_counts_for[std::move(name)].second = cur; } else { - // ignore other tensors - } - } - - for (const auto & sc : sums_counts_for) { - const std::string & name = sc.first; - const struct ggml_tensor * in_sum2 = sc.second.first; - const struct ggml_tensor * counts = sc.second.second; - - if (!in_sum2 || !counts) { - LOG_ERR("%s: mismatched sums and counts for %s\n", __func__, name.c_str()); - gguf_free(ctx_gguf); - ggml_free(ctx); - return false; - } - - auto & e = m_stats[name]; - - int64_t nval = ggml_nelements(in_sum2); - if (e.values.empty()) { - e.values.resize(nval, 0.0f); - } else if ((size_t) nval != e.values.size()) { - LOG_ERR("%s: mismatched sums size for %s: %zu != %zu\n", __func__, name.c_str(), (size_t) nval, e.values.size()); - gguf_free(ctx_gguf); - ggml_free(ctx); - return false; - } + // GGUF format: raw sums and counts, accumulate directly + const int64_t nval = entry.sums.size(); + const int64_t ncounts = entry.counts.size(); + + if (e.values.empty()) { + e.values.resize(nval, 0.0f); + } else if ((size_t) nval != e.values.size()) { + LOG_ERR("%s: mismatched sums size for %s: %zu != %zu\n", __func__, name.c_str(), (size_t) nval, e.values.size()); + return false; + } - int64_t ncounts = ggml_nelements(counts); - if (e.counts.empty()) { - e.counts.resize(ncounts, 0); - } else if (e.counts.size() == 1 && ncounts > 1) { - // broadcast, when loading an old imatrix - e.counts.resize(ncounts, e.counts[0]); - } else if ((size_t) ncounts != e.counts.size()) { - LOG_ERR("%s: mismatched counts size for %s: %zu != %zu\n", __func__, name.c_str(), (size_t) ncounts, e.counts.size()); - gguf_free(ctx_gguf); - ggml_free(ctx); - return false; - } + if (e.counts.empty()) { + e.counts.resize(ncounts, 0); + } else if (e.counts.size() == 1 && ncounts > 1) { + e.counts.resize(ncounts, e.counts[0]); + } else if ((size_t) ncounts != e.counts.size()) { + LOG_ERR("%s: mismatched counts size for %s: %zu != %zu\n", __func__, name.c_str(), (size_t) ncounts, e.counts.size()); + return false; + } - // Recreate the state as expected by save_imatrix() - for (int64_t j = 0; j < nval; j++) { - e.values[j] += ((const float *) in_sum2->data)[j]; - } - for (int64_t j = 0; j < ncounts; j++) { - e.counts[j] += std::lround(((const float *) counts->data)[j]); + for (int64_t j = 0; j < nval; ++j) { + e.values[j] += entry.sums[j]; + } + for (int64_t j = 0; j < ncounts; ++j) { + e.counts[j] += entry.counts[j]; + } } } - // TODO: extract into its own method; this is also used by the legacy format + m_datasets.insert(m_datasets.end(), loaded.datasets.begin(), loaded.datasets.end()); + // Calculate the last chunk count int64_t max_count = 0; for (const auto & stats : m_stats) { @@ -831,10 +686,8 @@ bool IMatrixCollector::load_imatrix(const char * file_name) { } } } - m_last_chunk = max_count / (m_params.n_ctx / m_params.n_parallel); + m_last_chunk = max_count / chunk_size; - gguf_free(ctx_gguf); - ggml_free(ctx); return true; } @@ -1218,6 +1071,9 @@ int main(int argc, char ** argv) { return 1; } + // set_params before show_statistics so load_imatrix has valid n_ctx/n_parallel + g_collector.set_params(params); + if (params.show_statistics) { if (!show_statistics(params)) { return 1; diff --git a/tools/quantize/README.md b/tools/quantize/README.md index b8c225124b33..27384bebf697 100644 --- a/tools/quantize/README.md +++ b/tools/quantize/README.md @@ -5,62 +5,87 @@ Quantization reduces the precision of model weights (e.g., from 32-bit floats to This process however, may introduce some accuracy loss which is usually measured in [Perplexity](https://huggingface.co/docs/transformers/en/perplexity) (ppl) and/or [Kullback–Leibler Divergence](https://en.wikipedia.org/wiki/Kullback%E2%80%93Leibler_divergence) (kld). This can be minimized by using a suitable imatrix file. -You can also use the [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space on Hugging Face to build your own quants without any setup. +You can also use the [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space on Hugging Face to build your own quants without any setup. It syncs from llama.cpp `main` every 6 hours. -Note: It is synced from llama.cpp `main` every 6 hours. +## Overview -Example usage: +Quantization is done in two phases: +- Convert the original model to GGUF format. +- Quantize the converted GGUF file. -```./llama-quantize [options] input-model-f32.gguf [output-model-quant.gguf] type [threads]``` +If the model supports multimodal inputs (images or audio), you also need to convert and quantize the multimodal encoders and projectors. + +To perform these tasks, you need to install the Python requirements: ```bash -# from Hugginface, obtain the official meta-llama/Llama-3.1-8B model weights and place them in ./models -ls ./models -config.json model-00001-of-00004.safetensors model-00004-of-00004.safetensors README.md tokenizer.json -generation_config.json model-00002-of-00004.safetensors model.safetensors.index.json special_tokens_map.json USE_POLICY.md -LICENSE model-00003-of-00004.safetensors original tokenizer_config.json +python3 -m pip install -r requirements.txt +``` -# [Optional] for PyTorch .bin models like Mistral-7B -ls ./models - +Or if you use `uv`: -# install Python dependencies -python3 -m pip install -r requirements.txt +```bash +uv pip install -r requirements.txt --index-strategy unsafe-best-match +``` -# convert the model to ggml FP16 format -python3 convert_hf_to_gguf.py ./models/mymodel/ +## Prepare the input GGUF file -# quantize the model to 4-bits (using Q4_K_M method) -./llama-quantize ./models/mymodel/ggml-model-f16.gguf ./models/mymodel/ggml-model-Q4_K_M.gguf Q4_K_M +To convert a model from a Hugging Face repo, you can use a command like the following: -# update the gguf filetype to current version if older version is now unsupported -./llama-quantize ./models/mymodel/ggml-model-Q4_K_M.gguf ./models/mymodel/ggml-model-Q4_K_M-v2.gguf COPY ``` +python convert_hf_to_gguf.py --outfile gemma-4-E2B-it-bf16.gguf --outtype bf16 --remote google/gemma-4-E2B-it +``` + +Notes: +- In the usual case where the model is distributed in 16-bit format, `--outtype auto` (or omitting `--outtype` entirely) also works well. +- If you have previously downloaded the model locally, specify the directory and remove the `--remote` flag. +- For compatibility reasons, the Python requirements install transformers 4, but more and more models (like Gemma 4) require transformers 5. You can safely `pip install -U transformers` to get the latest version. + +## Quantize the GGUF -Run the quantized model: +After you have created a high-quality GGUF version of the model, you use `llama-quantize` to apply quantization. For example, quantize to `Q4_K_M` using a command like the following: ```bash -# start inference on a gguf model -./llama-cli -m ./models/mymodel/ggml-model-Q4_K_M.gguf -cnv -p "You are a helpful assistant" +./build/bin/llama-quantize gemma-4-E2B-it-bf16.gguf gemma-4-E2B-it-Q4_K_M.gguf Q4_K_M ``` +Various quantization methods are described [later in this document](#quantize). + Options: -* `--allow-requantize` allows requantizing tensors that have already been quantized. Warning: This can severely reduce quality compared to quantizing from 16bit or 32bit -* `--leave-output-tensor` will leave output.weight un(re)quantized. Increases model size but may also increase quality, especially when requantizing -* `--pure` disables k-quant mixtures and quantizes all tensors to the same type -* `--imatrix` uses data in file generated by `llama-imatrix` as importance matrix for quant optimizations (highly recommended) -* `--include-weights` use an importance matrix for tensor(s) in the list. Cannot be used with `--exclude-weights` -* `--exclude-weights` use an importance matrix for tensor(s) in the list. Cannot be used with `--include-weights` +* `--allow-requantize` allow requantizing tensors that have already been quantized. Warning: This can severely reduce quality compared to quantizing from 16bit or 32bit +* `--leave-output-tensor` leave output.weight un(re)quantized. Increases model size but may also increase quality, especially when requantizing +* `--pure` disable k-quant mixtures and quantizes all tensors to the same type +* `--imatrix file_name` use data in file_name as importance matrix for quant optimizations +* `--include-weights tensor_name` use importance matrix for this tensor (can be specified multiple times) +* `--exclude-weights tensor_name` use importance matrix for the tensors **not** specified (include/exclude cannot be mixed) * `--output-tensor-type` use a specific quant type for the output.weight tensor * `--token-embedding-type` use a specific quant type for the token embeddings tensor -* `--keep-split` will generate the quantized model in the same shards as the input file otherwise it will produce a single quantized file +* `--keep-split` generate the quantized model in the same shards as the input file instead of a single quantized file Advanced options: * `--tensor-type` quantize specific tensor(s) to specific quant types. Supports regex syntax. May be specified multiple times. * `--prune-layers` prune (remove) the layers in the list -* `--override-kv` option to override model metadata by key in the quantized model. May be specified multiple times +* `--override-kv` option to override model metadata by key in the quantized model. May be specified multiple times. + +## (Optional) Convert the multimodal components + +llama.cpp will convert the LLM portion of the source model, which is enough for conversational applications. If the model accepts multimodal inputs and you wish to take advantage of them, you need to create a separate GGUF file. This file is generically known as `mmproj`, for "multimedia projector"; however, it may contain various components such as vision or audio encoders in addition to projections. + +Multimodal components are usually much smaller than the LLMs they come with. In addition, their quality has a direct impact on the quality of LLM generations, because these components are in charge of preparing the inputs for the LLM: the closer inputs are to data seen during training, the better LLM results will be. + +For these reasons, multimodal components are usually kept in a high-quality format such as bf16 or q8. The impact on speed and memory from using a smaller quant is negligible, but overall quality could be impacted. + +```bash +python convert_hf_to_gguf.py --mmproj --outfile mmproj-gemma-4-E2B-it-Q8_0.gguf --outtype q8_0 --remote google/gemma-4-E2B-it +``` + +## Run the quantized model + + +```bash +./build/bin/llama cli -m ./gemma-4-E2B-it-Q4_K_M.gguf --mmproj ./mmproj-gemma-4-E2B-it-Q8_0.gguf --image --prompt "Describe this image" +``` -Examples: +## Quantization Examples ```bash # naive Q4_K_M quantization using default settings and 8 CPU threads. Output will be "ggml-model-Q4_K_M.gguf" diff --git a/tools/quantize/quantize.cpp b/tools/quantize/quantize.cpp index 7292bda6f4ef..840eefc2f5ac 100644 --- a/tools/quantize/quantize.cpp +++ b/tools/quantize/quantize.cpp @@ -2,6 +2,7 @@ #include "build-info.h" #include "common.h" +#include "imatrix-loader.h" #include "gguf.h" @@ -14,7 +15,6 @@ #include #include #include -#include #include #include @@ -78,11 +78,6 @@ static const char * const LLM_KV_QUANTIZE_IMATRIX_DATASET = "quantize.imatrix static const char * const LLM_KV_QUANTIZE_IMATRIX_N_ENTRIES = "quantize.imatrix.entries_count"; static const char * const LLM_KV_QUANTIZE_IMATRIX_N_CHUNKS = "quantize.imatrix.chunks_count"; -// TODO: share with imatrix.cpp -static const char * const LLM_KV_IMATRIX_DATASETS = "imatrix.datasets"; -static const char * const LLM_KV_IMATRIX_CHUNK_COUNT = "imatrix.chunk_count"; -static const char * const LLM_KV_IMATRIX_CHUNK_SIZE = "imatrix.chunk_size"; - static bool striequals(const char * a, const char * b) { while (*a && *b) { if (std::tolower(*a) != std::tolower(*b)) { @@ -181,184 +176,84 @@ static void usage(const char * executable) { exit(1); } -static int load_legacy_imatrix(const std::string & imatrix_file, std::vector & imatrix_datasets, std::unordered_map> & imatrix_data) { - std::ifstream in(imatrix_file.c_str(), std::ios::binary); - if (!in) { - printf("%s: failed to open %s\n",__func__, imatrix_file.c_str()); - exit(1); - } - int n_entries; - in.read((char *)&n_entries, sizeof(n_entries)); - if (in.fail() || n_entries < 1) { - printf("%s: no data in file %s\n", __func__, imatrix_file.c_str()); - exit(1); - } - for (int i = 0; i < n_entries; ++i) { - int len; in.read((char *)&len, sizeof(len)); - std::vector name_as_vec(len+1); - in.read((char *)name_as_vec.data(), len); - if (in.fail()) { - printf("%s: failed reading name for entry %d from %s\n", __func__, i+1, imatrix_file.c_str()); - exit(1); - } - name_as_vec[len] = 0; - std::string name{name_as_vec.data()}; - auto & e = imatrix_data[name]; - int ncall; - in.read((char *)&ncall, sizeof(ncall)); - int nval; - in.read((char *)&nval, sizeof(nval)); - if (in.fail() || nval < 1) { - printf("%s: failed reading number of values for entry %d\n", __func__, i); - imatrix_data = {}; - exit(1); - } - e.resize(nval); - in.read((char *)e.data(), nval*sizeof(float)); - if (in.fail()) { - printf("%s: failed reading data for entry %d\n", __func__, i); - imatrix_data = {}; - exit(1); - } - if (ncall > 0) { - for (auto & v : e) { - v /= ncall; - } - } - - if (getenv("LLAMA_TRACE")) { - printf("%s: loaded data (size = %6d, ncall = %6d) for '%s'\n", __func__, int(e.size()), ncall, name.c_str()); - } - } - - // latest legacy imatrix version contains the dataset filename at the end of the file - int m_last_call = 0; - if (in.peek() != EOF) { - in.read((char *)&m_last_call, sizeof(m_last_call)); - int dataset_len; - in.read((char *)&dataset_len, sizeof(dataset_len)); - std::vector dataset_as_vec(dataset_len); - in.read(dataset_as_vec.data(), dataset_len); - imatrix_datasets.resize(1); - imatrix_datasets[0].assign(dataset_as_vec.begin(), dataset_as_vec.end()); - printf("%s: imatrix dataset='%s'\n", __func__, imatrix_datasets[0].c_str()); - } - printf("%s: loaded %d importance matrix entries from %s computed on %d chunks\n", __func__, int(imatrix_data.size()), imatrix_file.c_str(), m_last_call); - return m_last_call; -} - static int load_imatrix(const std::string & imatrix_file, std::vector & imatrix_datasets, std::unordered_map> & imatrix_data) { - - struct ggml_context * ctx = nullptr; - struct gguf_init_params meta_gguf_params = { - /* .no_alloc = */ false, // the data is needed - /* .ctx = */ &ctx, - }; - struct gguf_context * ctx_gguf = gguf_init_from_file(imatrix_file.c_str(), meta_gguf_params); - if (!ctx_gguf) { - fprintf(stderr, "%s: imatrix file '%s' is using old format\n", __func__, imatrix_file.c_str()); - return load_legacy_imatrix(imatrix_file, imatrix_datasets, imatrix_data); - } - const int32_t n_entries = gguf_get_n_tensors(ctx_gguf); - if (n_entries < 1) { - fprintf(stderr, "%s: no data in file %s\n", __func__, imatrix_file.c_str()); - gguf_free(ctx_gguf); - ggml_free(ctx); + common_imatrix loaded; + if (!common_imatrix_load(imatrix_file, loaded)) { + fprintf(stderr, "%s: failed to load imatrix from '%s'\n", __func__, imatrix_file.c_str()); exit(1); } - const int dataset_idx = gguf_find_key(ctx_gguf, LLM_KV_IMATRIX_DATASETS); - const int chunk_count_idx = gguf_find_key(ctx_gguf, LLM_KV_IMATRIX_CHUNK_COUNT); - const int chunk_size_idx = gguf_find_key(ctx_gguf, LLM_KV_IMATRIX_CHUNK_SIZE); - if (dataset_idx < 0 || chunk_count_idx < 0 || chunk_size_idx < 0) { + if (!loaded.is_legacy && !loaded.has_metadata) { fprintf(stderr, "%s: missing imatrix metadata in file %s\n", __func__, imatrix_file.c_str()); - gguf_free(ctx_gguf); - ggml_free(ctx); exit(1); } - const uint32_t chunk_size = gguf_get_val_u32(ctx_gguf, chunk_size_idx); - - const std::string sums_suffix{ ".in_sum2" }; - const std::string counts_suffix{ ".counts" }; - - // Using an ordered map to get a deterministic iteration order. - std::map> sums_counts_for; - - for (struct ggml_tensor * cur = ggml_get_first_tensor(ctx); cur; cur = ggml_get_next_tensor(ctx, cur)) { - std::string name = cur->name; - - if (name.empty()) { continue; } + for (const auto & [name, entry] : loaded.entries) { + auto & e = imatrix_data[name]; + e.resize(entry.sums.size()); + + if (!loaded.is_legacy) { + // GGUF format: normalize by per-expert counts + const int64_t ncounts = entry.counts.size(); + const int64_t ne0 = (int64_t) entry.sums.size() / ncounts; + + for (int64_t j = 0; j < ncounts; ++j) { + const float count = (float) entry.counts[j]; + if (count > 0.0f) { + for (int64_t i = 0; i < ne0; ++i) { + e[j*ne0 + i] = entry.sums[j*ne0 + i] / count; + } + } else { + for (int64_t i = 0; i < ne0; ++i) { + e[j*ne0 + i] = 1; + } + } + } - if (string_remove_suffix(name, sums_suffix)) { - // in_sum2 - sums_counts_for[std::move(name)].first = cur; - } else if (string_remove_suffix(name, counts_suffix)) { - // counts - sums_counts_for[std::move(name)].second = cur; + if (getenv("LLAMA_TRACE")) { + float max_count = 0.0f; + for (int64_t j = 0; j < ncounts; ++j) { + const float count = (float) entry.counts[j]; + if (count > max_count) { + max_count = count; + } + } + printf("%s: loaded data (size = %6d, n_tokens = %6d, n_chunks = %6d) for '%s'\n", + __func__, int(e.size()), int(max_count), int(max_count / loaded.chunk_size), name.c_str()); + } } else { - // ignore other tensors - } - } - - for (const auto & sc : sums_counts_for) { - const std::string & name = sc.first; - const struct ggml_tensor * sums = sc.second.first; - const struct ggml_tensor * counts = sc.second.second; - - if (!sums || !counts) { - fprintf(stderr, "%s: mismatched sums and counts for %s\n", __func__, name.c_str()); - gguf_free(ctx_gguf); - ggml_free(ctx); - exit(1); - } - - const int64_t ne0 = sums->ne[0]; - const int64_t ne1 = sums->ne[1]; - - auto & e = imatrix_data[name]; - e.resize(ggml_nelements(sums)); - float max_count = 0.0f; - for (int64_t j = 0; j < ne1; ++j) { - const float count = ((const float *) counts->data)[j]; - if (count > 0.0f) { - for (int64_t i = 0; i < ne0; ++i) { - e[j*ne0 + i] = ((const float *) sums->data)[j*ne0 + i] / count; + // Legacy format: sums contain (raw/count)*ncall, divide by ncall + const int64_t ncall = entry.counts.empty() ? 0 : entry.counts[0]; + if (ncall > 0) { + for (size_t i = 0; i < entry.sums.size(); ++i) { + e[i] = entry.sums[i] / ncall; } } else { - // Partial imatrix data, this tensor never got any input during calibration - for (int64_t i = 0; i < ne0; ++i) { - e[j*ne0 + i] = 1; + for (size_t i = 0; i < entry.sums.size(); ++i) { + e[i] = entry.sums[i]; } } - if (count > max_count) { - max_count = count; + + if (getenv("LLAMA_TRACE")) { + printf("%s: loaded data (size = %6d, ncall = %6d) for '%s'\n", + __func__, int(e.size()), int(ncall), name.c_str()); } } - if (getenv("LLAMA_TRACE")) { - printf("%s: loaded data (size = %6d, n_tokens = %6d, n_chunks = %6d) for '%s'\n", __func__, int(e.size()), int(max_count), int(max_count / chunk_size), name.c_str()); - } } - int m_last_chunk = gguf_get_val_u32(ctx_gguf, chunk_count_idx); + imatrix_datasets = std::move(loaded.datasets); - int64_t n_datasets = gguf_get_arr_n(ctx_gguf, dataset_idx); - imatrix_datasets.reserve(n_datasets); - for (int64_t i = 0; i < n_datasets; ++i) { - imatrix_datasets.push_back(gguf_get_arr_str(ctx_gguf, dataset_idx, i)); - } - printf("%s: imatrix datasets=['%s'", __func__, imatrix_datasets[0].c_str()); - for (size_t i = 1; i < imatrix_datasets.size(); ++i) { - printf(", '%s'", imatrix_datasets[i].c_str()); + if (!imatrix_datasets.empty()) { + printf("%s: imatrix datasets=['%s'", __func__, imatrix_datasets[0].c_str()); + for (size_t i = 1; i < imatrix_datasets.size(); ++i) { + printf(", '%s'", imatrix_datasets[i].c_str()); + } + printf("]\n"); } - printf("]\n"); - - printf("%s: loaded %d importance matrix entries from %s computed on %d chunks\n", __func__, int(imatrix_data.size()), imatrix_file.c_str(), m_last_chunk); - gguf_free(ctx_gguf); - ggml_free(ctx); + printf("%s: loaded %d importance matrix entries from %s computed on %d chunks\n", __func__, int(imatrix_data.size()), imatrix_file.c_str(), loaded.chunk_count); - return m_last_chunk; + return loaded.chunk_count; } static int prepare_imatrix(const std::string & imatrix_file, diff --git a/tools/server/server-context.cpp b/tools/server/server-context.cpp index 28f738c3feb2..80119c8c8387 100644 --- a/tools/server/server-context.cpp +++ b/tools/server/server-context.cpp @@ -10,6 +10,8 @@ #include "common.h" #include "fit.h" #include "llama.h" +#include "../../src/llama-ext.h" // staging API: llama_set_mtp_source +#include "ggml-cpp.h" #include "log.h" #include "sampling.h" #include "speculative.h" @@ -845,11 +847,27 @@ struct server_context_impl { } cparams_dft.n_rs_seq = 0; + bool skip_measure = false; + //TODO: remove this + if (spec_mtp && has_draft) { + struct gguf_init_params meta_params = { + /* .no_alloc = */ true, + /* .ctx = */ nullptr, + }; + gguf_context_ptr meta(gguf_init_from_file(params_dft.model.path.c_str(), meta_params)); + + if (std::string(gguf_get_val_str(meta.get(), gguf_find_key(meta.get(), "general.architecture"))) == "gemma4-assistant") { + skip_measure = true; + SRV_WRN("[spec] skipping --fit memory measurement for Gemma 4 assistant draft model '%s'\n", + params_dft.model.path.c_str()); + } + } + std::vector devs; uint32_t hp_ngl = 0; uint32_t hp_nct = 0; uint32_t hp_nex = 0; - try { + if (!skip_measure) try { auto dmd = common_get_device_memory_data( params_dft.model.path.c_str(), &mparams_dft, &cparams_dft, devs, hp_ngl, hp_nct, hp_nex, GGML_LOG_LEVEL_ERROR); @@ -912,13 +930,23 @@ struct server_context_impl { SRV_INF("loading draft model '%s'\n", params_spec.mparams.path.c_str()); + const bool spec_mtp = std::find(params_base.speculative.types.begin(), + params_base.speculative.types.end(), + COMMON_SPECULATIVE_TYPE_DRAFT_MTP) != params_base.speculative.types.end(); + auto params_dft = params_base; params_dft.devices = params_spec.devices; params_dft.model = params_spec.mparams; params_dft.n_gpu_layers = params_spec.n_gpu_layers; - params_dft.cache_type_k = params_spec.cache_type_k; - params_dft.cache_type_v = params_spec.cache_type_v; + // TODO: find a better way to expose that the cache is shared + if (spec_mtp) { + params_dft.cache_type_k = params_base.cache_type_k; + params_dft.cache_type_v = params_base.cache_type_v; + } else { + params_dft.cache_type_k = params_spec.cache_type_k; + params_dft.cache_type_v = params_spec.cache_type_v; + } if (params_spec.cpuparams.n_threads > 0) { params_dft.cpuparams.n_threads = params_spec.cpuparams.n_threads; @@ -937,9 +965,6 @@ struct server_context_impl { auto cparams = common_context_params_to_llama(params_dft); - const bool spec_mtp = std::find(params_base.speculative.types.begin(), - params_base.speculative.types.end(), - COMMON_SPECULATIVE_TYPE_DRAFT_MTP) != params_base.speculative.types.end(); if (spec_mtp) { cparams.ctx_type = LLAMA_CONTEXT_TYPE_MTP; } @@ -949,6 +974,11 @@ struct server_context_impl { cparams.n_rs_seq = 0; ctx_dft.reset(llama_init_from_model(model_dft.get(), cparams)); + if (spec_mtp) { + // MTP draft must know its target before the first decode + llama_set_mtp_source(ctx_dft.get(), ctx_tgt); + } + ctx_dft_seq_rm_type = common_context_can_seq_rm(ctx_dft.get()); params_base.speculative.draft.ctx_tgt = ctx_tgt; @@ -971,6 +1001,10 @@ struct server_context_impl { return false; } + // wire the source before any decode (the seq-rm probe below + // triggers sched_reserve which needs src for Gemma4-style MTP) + llama_set_mtp_source(ctx_dft.get(), ctx_tgt); + ctx_dft_seq_rm_type = common_context_can_seq_rm(ctx_dft.get()); params_base.speculative.draft.ctx_tgt = ctx_tgt; @@ -2512,7 +2546,7 @@ struct server_context_impl { llama_memory_seq_pos_max(llama_get_memory(ctx_tgt), slot.id)); if (use_ckpt_dft) { - slot.spec_ckpt.update_dft(ctx_dft.get(), slot.id, LLAMA_STATE_SEQ_FLAGS_PARTIAL_ONLY | LLAMA_STATE_SEQ_FLAGS_ON_DEVICE); + slot.spec_ckpt.update_dft(ctx_dft.get(), slot.id, LLAMA_STATE_SEQ_FLAGS_PARTIAL_ONLY); } slot.spec_prompt = slot.prompt.tokens.get_text_tokens(); @@ -2551,7 +2585,7 @@ struct server_context_impl { if (ctx_dft) { if (use_ckpt_dft) { - ckpt.load_dft(ctx_dft.get(), slot.id, LLAMA_STATE_SEQ_FLAGS_PARTIAL_ONLY | LLAMA_STATE_SEQ_FLAGS_ON_DEVICE); + ckpt.load_dft(ctx_dft.get(), slot.id, LLAMA_STATE_SEQ_FLAGS_PARTIAL_ONLY); } common_context_seq_rm(ctx_dft.get(), slot.id, ckpt.pos_max + 1, -1); @@ -2568,7 +2602,7 @@ struct server_context_impl { if (use_ckpt_tgt) { //const int64_t t_start = ggml_time_us(); - ckpt.update_tgt(ctx_tgt, slot.id, LLAMA_STATE_SEQ_FLAGS_PARTIAL_ONLY | LLAMA_STATE_SEQ_FLAGS_ON_DEVICE); + ckpt.update_tgt(ctx_tgt, slot.id, LLAMA_STATE_SEQ_FLAGS_PARTIAL_ONLY); //const int64_t t_total = ggml_time_us() - t_start; //printf("checkpoint total: %f ms\n", t_total / 1000.0); @@ -2580,7 +2614,7 @@ struct server_context_impl { } if (use_ckpt_dft) { - ckpt.update_dft(ctx_dft.get(), slot.id, LLAMA_STATE_SEQ_FLAGS_PARTIAL_ONLY | LLAMA_STATE_SEQ_FLAGS_ON_DEVICE); + ckpt.update_dft(ctx_dft.get(), slot.id, LLAMA_STATE_SEQ_FLAGS_PARTIAL_ONLY); } } } @@ -3447,13 +3481,13 @@ struct server_context_impl { SLT_DBG(slot, "restoring speculative checkpoint (pos_min = %d, pos_max = %d, size = %zu)\n", ckpt.pos_min, ckpt.pos_max, ckpt.size()); { - ckpt.load_tgt(slot.ctx_tgt, slot.id, LLAMA_STATE_SEQ_FLAGS_PARTIAL_ONLY | LLAMA_STATE_SEQ_FLAGS_ON_DEVICE); + ckpt.load_tgt(slot.ctx_tgt, slot.id, LLAMA_STATE_SEQ_FLAGS_PARTIAL_ONLY); common_context_seq_rm(slot.ctx_tgt, slot.id, ckpt.pos_max + 1, -1); } if (slot.ctx_dft) { - ckpt.load_dft(slot.ctx_dft, slot.id, LLAMA_STATE_SEQ_FLAGS_PARTIAL_ONLY | LLAMA_STATE_SEQ_FLAGS_ON_DEVICE); + ckpt.load_dft(slot.ctx_dft, slot.id, LLAMA_STATE_SEQ_FLAGS_PARTIAL_ONLY); common_context_seq_rm(slot.ctx_dft, slot.id, ckpt.pos_max + 1, -1); } diff --git a/tools/ui/package-lock.json b/tools/ui/package-lock.json index 06f885680a6b..ffd4f6ca029a 100644 --- a/tools/ui/package-lock.json +++ b/tools/ui/package-lock.json @@ -7,77 +7,76 @@ "": { "name": "llama-ui", "version": "1.0.0", - "dependencies": { - "@modelcontextprotocol/sdk": "^1.25.1", - "highlight.js": "^11.11.1", - "mermaid": "^11.15.0", - "mode-watcher": "^1.1.0", - "pdfjs-dist": "^5.4.54", - "rehype-highlight": "^7.0.2", - "rehype-stringify": "^10.0.1", - "remark": "^15.0.1", - "remark-breaks": "^4.0.0", - "remark-gfm": "^4.0.1", - "remark-html": "^16.0.1", - "remark-rehype": "^11.1.2", - "svelte-sonner": "^1.0.5", - "unist-util-visit": "^5.0.0", - "zod": "^4.2.1" - }, "devDependencies": { - "@chromatic-com/storybook": "^5.0.0", - "@eslint/compat": "^1.2.5", - "@eslint/js": "^9.18.0", - "@internationalized/date": "^3.10.1", - "@lucide/svelte": "^0.515.0", - "@playwright/test": "^1.49.1", - "@storybook/addon-a11y": "^10.2.4", - "@storybook/addon-docs": "^10.2.4", - "@storybook/addon-svelte-csf": "^5.0.10", - "@storybook/addon-vitest": "^10.2.4", - "@storybook/sveltekit": "^10.2.4", - "@sveltejs/adapter-static": "^3.0.10", - "@sveltejs/kit": "^2.48.4", - "@sveltejs/vite-plugin-svelte": "^6.2.1", - "@tailwindcss/forms": "^0.5.9", - "@tailwindcss/typography": "^0.5.15", - "@tailwindcss/vite": "^4.0.0", + "@chromatic-com/storybook": "5.0.0", + "@eslint/compat": "1.4.1", + "@eslint/js": "9.39.2", + "@internationalized/date": "3.10.1", + "@lucide/svelte": "0.515.0", + "@modelcontextprotocol/sdk": "1.26.0", + "@playwright/test": "1.56.1", + "@storybook/addon-a11y": "10.2.4", + "@storybook/addon-docs": "10.2.4", + "@storybook/addon-svelte-csf": "5.0.10", + "@storybook/addon-vitest": "10.2.4", + "@storybook/sveltekit": "10.2.4", + "@sveltejs/adapter-static": "3.0.10", + "@sveltejs/kit": "2.60.1", + "@sveltejs/vite-plugin-svelte": "6.2.1", + "@tailwindcss/forms": "0.5.10", + "@tailwindcss/typography": "0.5.16", + "@tailwindcss/vite": "4.1.11", "@types/node": "^24", - "@vitest/browser": "^3.2.3", - "@vitest/coverage-v8": "^3.2.3", - "bits-ui": "^2.14.4", - "clsx": "^2.1.1", - "dexie": "^4.0.11", - "eslint": "^9.18.0", - "eslint-config-prettier": "^10.0.1", - "eslint-plugin-storybook": "^10.2.4", - "eslint-plugin-svelte": "^3.0.0", - "globals": "^16.0.0", - "http-server": "^14.1.1", - "mdast": "^3.0.0", - "mdsvex": "^0.12.3", - "playwright": "^1.56.1", - "prettier": "^3.4.2", - "prettier-plugin-svelte": "^3.3.3", - "prettier-plugin-tailwindcss": "^0.6.11", - "rehype-katex": "^7.0.1", - "remark-math": "^6.0.0", - "sass": "^1.93.3", - "storybook": "^10.2.4", - "svelte": "^5.38.2", - "svelte-check": "^4.0.0", - "tailwind-merge": "^3.3.1", - "tailwind-variants": "^3.2.2", - "tailwindcss": "^4.0.0", - "tw-animate-css": "^1.3.5", - "typescript": "^5.0.0", - "typescript-eslint": "^8.20.0", - "unified": "^11.0.5", - "uuid": "^13.0.0", - "vite": "^7.2.2", - "vite-plugin-devtools-json": "^0.2.0", - "vitest": "^3.2.3", - "vitest-browser-svelte": "^0.1.0" + "@vitest/browser": "4.1.8", + "@vitest/browser-playwright": "4.1.8", + "@vitest/coverage-v8": "4.1.8", + "bits-ui": "2.18.1", + "clsx": "2.1.1", + "dexie": "4.0.11", + "eslint": "9.39.2", + "eslint-config-prettier": "10.1.8", + "eslint-plugin-storybook": "10.2.4", + "eslint-plugin-svelte": "3.15.0", + "globals": "16.3.0", + "highlight.js": "11.11.1", + "http-server": "14.1.1", + "mdast": "3.0.0", + "mdsvex": "0.12.6", + "mermaid": "11.15.0", + "mode-watcher": "1.1.0", + "pdfjs-dist": "5.4.54", + "playwright": "1.56.1", + "prettier": "3.6.2", + "prettier-plugin-svelte": "3.4.0", + "prettier-plugin-tailwindcss": "0.6.14", + "rehype-highlight": "7.0.2", + "rehype-katex": "7.0.1", + "rehype-stringify": "10.0.1", + "remark": "15.0.1", + "remark-breaks": "4.0.0", + "remark-gfm": "4.0.1", + "remark-html": "16.0.1", + "remark-math": "6.0.0", + "remark-rehype": "11.1.2", + "sass": "1.93.3", + "storybook": "10.3.3", + "svelte": "5.55.7", + "svelte-check": "4.3.0", + "svelte-sonner": "1.0.5", + "tailwind-merge": "3.3.1", + "tailwind-variants": "3.2.2", + "tailwindcss": "4.1.11", + "tw-animate-css": "1.3.5", + "typescript": "5.8.3", + "typescript-eslint": "8.56.0", + "unified": "11.0.5", + "unist-util-visit": "5.0.0", + "uuid": "13.0.2", + "vite": "7.3.2", + "vite-plugin-devtools-json": "0.2.1", + "vitest": "4.1.8", + "vitest-browser-svelte": "2.1.1", + "zod": "4.2.1" } }, "node_modules/@adobe/css-tools": { @@ -105,6 +104,7 @@ "version": "1.1.0", "resolved": "https://registry.npmjs.org/@antfu/install-pkg/-/install-pkg-1.1.0.tgz", "integrity": "sha512-MGQsmw10ZyI+EJo45CdSER4zEb+p31LpDAFp2Z3gkSd1yqVZGi0Ebx++YTEMonJy4oChEMLsxZ64j8FH6sSqtQ==", + "dev": true, "license": "MIT", "dependencies": { "package-manager-detector": "^1.3.0", @@ -114,23 +114,15 @@ "url": "https://github.com/sponsors/antfu" } }, - "node_modules/@antfu/install-pkg/node_modules/tinyexec": { - "version": "1.1.2", - "resolved": "https://registry.npmjs.org/tinyexec/-/tinyexec-1.1.2.tgz", - "integrity": "sha512-dAqSqE/RabpBKI8+h26GfLq6Vb3JVXs30XYQjdMjaj/c2tS8IYYMbIzP599KtRj7c57/wYApb3QjgRgXmrCukA==", - "license": "MIT", - "engines": { - "node": ">=18" - } - }, "node_modules/@babel/code-frame": { - "version": "7.27.1", - "resolved": "https://registry.npmjs.org/@babel/code-frame/-/code-frame-7.27.1.tgz", - "integrity": "sha512-cjQ7ZlQ0Mv3b47hABuTevyTuYN4i+loJKGeV9flcCgIK37cCXRh+L1bd3iBHlynerhQ7BhCkn2BPbQUL+rGqFg==", + "version": "7.29.7", + "resolved": "https://registry.npmjs.org/@babel/code-frame/-/code-frame-7.29.7.tgz", + "integrity": "sha512-Aup7aUOfpbAUg2ROOJN6Iw5f9DMBlzu0mIkm/malLQFN/YQgO48wCj0Kxa3sEHJvPVFg7siR+qRInwXd2qhQKw==", "dev": true, "license": "MIT", + "peer": true, "dependencies": { - "@babel/helper-validator-identifier": "^7.27.1", + "@babel/helper-validator-identifier": "^7.29.7", "js-tokens": "^4.0.0", "picocolors": "^1.1.1" }, @@ -138,10 +130,18 @@ "node": ">=6.9.0" } }, + "node_modules/@babel/code-frame/node_modules/js-tokens": { + "version": "4.0.0", + "resolved": "https://registry.npmjs.org/js-tokens/-/js-tokens-4.0.0.tgz", + "integrity": "sha512-RdJUflcE3cUzKiMqQgsCu06FPu9UdIJO0beYbPhHN4k6apgJtifcoCtT9bcxOpYBtpD2kCM6Sbzg4CausW/PKQ==", + "dev": true, + "license": "MIT", + "peer": true + }, "node_modules/@babel/helper-string-parser": { - "version": "7.27.1", - "resolved": "https://registry.npmjs.org/@babel/helper-string-parser/-/helper-string-parser-7.27.1.tgz", - "integrity": "sha512-qMlSxKbpRlAridDExk92nSobyDdpPijUq2DW6oDnUqd0iOGxmQjyqhMIihI9+zv4LPyZdRje2cavWPbCbWm3eA==", + "version": "7.29.7", + "resolved": "https://registry.npmjs.org/@babel/helper-string-parser/-/helper-string-parser-7.29.7.tgz", + "integrity": "sha512-Pb5ijPrZ89GDH8223L4UP8i6QApWxs04RbPQJTeWDV0/keR2E36MeKnyr6LYmUUvqRRI+Iv87SuF1W6ErINzYw==", "dev": true, "license": "MIT", "engines": { @@ -149,9 +149,9 @@ } }, "node_modules/@babel/helper-validator-identifier": { - "version": "7.28.5", - "resolved": "https://registry.npmjs.org/@babel/helper-validator-identifier/-/helper-validator-identifier-7.28.5.tgz", - "integrity": "sha512-qSs4ifwzKJSV39ucNjsvc6WVHs6b7S03sOh2OcHF9UHfVPqWWALUsNUVzhSBiItjRZoLHx7nIarVjqKVusUZ1Q==", + "version": "7.29.7", + "resolved": "https://registry.npmjs.org/@babel/helper-validator-identifier/-/helper-validator-identifier-7.29.7.tgz", + "integrity": "sha512-qehxGkRj55h/ff8EMaJ+cYhyaKlHIxqYDn682wQD7RNp9UujOQsHog2uS0r2vzr4pW+sXf90NeeayjcNaX3fFg==", "dev": true, "license": "MIT", "engines": { @@ -159,13 +159,13 @@ } }, "node_modules/@babel/parser": { - "version": "7.29.0", - "resolved": "https://registry.npmjs.org/@babel/parser/-/parser-7.29.0.tgz", - "integrity": "sha512-IyDgFV5GeDUVX4YdF/3CPULtVGSXXMLh1xVIgdCgxApktqnQV0r7/8Nqthg+8YLGaAtdyIlo2qIdZrbCv4+7ww==", + "version": "7.29.7", + "resolved": "https://registry.npmjs.org/@babel/parser/-/parser-7.29.7.tgz", + "integrity": "sha512-hnORnjP/1P/zFEndoeX+n+t1RwWRJiJpM/jO7FW32Kn9r5+sJB2JWOdYo4L6k78j15eCwY3Gm/7364B1EMwtNg==", "dev": true, "license": "MIT", "dependencies": { - "@babel/types": "^7.29.0" + "@babel/types": "^7.29.7" }, "bin": { "parser": "bin/babel-parser.js" @@ -175,24 +175,25 @@ } }, "node_modules/@babel/runtime": { - "version": "7.27.6", - "resolved": "https://registry.npmjs.org/@babel/runtime/-/runtime-7.27.6.tgz", - "integrity": "sha512-vbavdySgbTTrmFE+EsiqUTzlOr5bzlnJtUv9PynGCAKvfQqjIXbvFdumPM/GxMDfyuGMJaJAU6TO4zc1Jf1i8Q==", + "version": "7.29.7", + "resolved": "https://registry.npmjs.org/@babel/runtime/-/runtime-7.29.7.tgz", + "integrity": "sha512-Nq8OhGWiZIZGV6hLHoyAKLLcJihP/xFeBMGJoUrxTX2psI8dCifzLhZISFb+VWS3wFMRDmCGw5R+dOySCqPLhw==", "dev": true, "license": "MIT", + "peer": true, "engines": { "node": ">=6.9.0" } }, "node_modules/@babel/types": { - "version": "7.29.0", - "resolved": "https://registry.npmjs.org/@babel/types/-/types-7.29.0.tgz", - "integrity": "sha512-LwdZHpScM4Qz8Xw2iKSzS+cfglZzJGvofQICy7W7v4caru4EaAmyUuO6BGrbyQ2mYV11W0U8j5mBhd14dd3B0A==", + "version": "7.29.7", + "resolved": "https://registry.npmjs.org/@babel/types/-/types-7.29.7.tgz", + "integrity": "sha512-4zBIxpPzowiZpusoFkyGVwakdRJUyuH5PxQ/PrqghfdFWWasvnCdPfQXHrenDai+gyLARulZjZowCOj6fjT4pA==", "dev": true, "license": "MIT", "dependencies": { - "@babel/helper-string-parser": "^7.27.1", - "@babel/helper-validator-identifier": "^7.28.5" + "@babel/helper-string-parser": "^7.29.7", + "@babel/helper-validator-identifier": "^7.29.7" }, "engines": { "node": ">=6.9.0" @@ -208,16 +209,25 @@ "node": ">=18" } }, + "node_modules/@blazediff/core": { + "version": "1.9.1", + "resolved": "https://registry.npmjs.org/@blazediff/core/-/core-1.9.1.tgz", + "integrity": "sha512-ehg3jIkYKulZh+8om/O25vkvSsXXwC+skXmyA87FFx6A/45eqOkZsBltMw/TVteb0mloiGT8oGRTcjRAz66zaA==", + "dev": true, + "license": "MIT" + }, "node_modules/@braintree/sanitize-url": { "version": "7.1.2", "resolved": "https://registry.npmjs.org/@braintree/sanitize-url/-/sanitize-url-7.1.2.tgz", "integrity": "sha512-jigsZK+sMF/cuiB7sERuo9V7N9jx+dhmHHnQyDSVdpZwVutaBu7WvNYqMDLSgFgfB30n452TP3vjDAvFC973mA==", + "dev": true, "license": "MIT" }, "node_modules/@chevrotain/types": { "version": "11.1.2", "resolved": "https://registry.npmjs.org/@chevrotain/types/-/types-11.1.2.tgz", "integrity": "sha512-U+HFai5+zmJCkK86QsaJtoITlboZHBqrVketcO2ROv865xfCMSFpELQoz1GkX5GzME8pTa+3kbKrZHQtI0gdbw==", + "dev": true, "license": "Apache-2.0" }, "node_modules/@chromatic-com/storybook": { @@ -893,6 +903,7 @@ "version": "1.19.13", "resolved": "https://registry.npmjs.org/@hono/node-server/-/node-server-1.19.13.tgz", "integrity": "sha512-TsQLe4i2gvoTtrHje625ngThGBySOgSK3Xo2XRYOdqGN1teR8+I7vchQC46uLJi8OF62YTYA3AhSpumtkhsaKQ==", + "dev": true, "license": "MIT", "engines": { "node": ">=18.14.1" @@ -971,12 +982,14 @@ "version": "2.0.0", "resolved": "https://registry.npmjs.org/@iconify/types/-/types-2.0.0.tgz", "integrity": "sha512-+wluvCrRhXrhyOmRDJ3q8mux9JkKy5SJ/v8ol2tu4FVjyYvtEzkc/3pK15ET6RKg4b4w4BmTk1+gsCUhf21Ykg==", + "dev": true, "license": "MIT" }, "node_modules/@iconify/utils": { "version": "3.1.3", "resolved": "https://registry.npmjs.org/@iconify/utils/-/utils-3.1.3.tgz", "integrity": "sha512-LPKOXPn/zV+zis1oOfGWogaXVpqUybF3ZS6SCZIsz8vg0ivVp9+fVqyYB7xq0aiST/VhUQYGO1qo6uoYSiEJqw==", + "dev": true, "license": "MIT", "dependencies": { "@antfu/install-pkg": "^1.1.0", @@ -994,24 +1007,6 @@ "@swc/helpers": "^0.5.0" } }, - "node_modules/@isaacs/cliui": { - "version": "8.0.2", - "resolved": "https://registry.npmjs.org/@isaacs/cliui/-/cliui-8.0.2.tgz", - "integrity": "sha512-O8jcjabXaleOG9DQ0+ARXWZBTfnP4WNAqzuiJK7ll44AmxGKv/J2M4TPjxjY3znBCfvBXFzucm1twdyFybFqEA==", - "dev": true, - "license": "ISC", - "dependencies": { - "string-width": "^5.1.2", - "string-width-cjs": "npm:string-width@^4.2.0", - "strip-ansi": "^7.0.1", - "strip-ansi-cjs": "npm:strip-ansi@^6.0.1", - "wrap-ansi": "^8.1.0", - "wrap-ansi-cjs": "npm:wrap-ansi@^7.0.0" - }, - "engines": { - "node": ">=12" - } - }, "node_modules/@isaacs/fs-minipass": { "version": "4.0.1", "resolved": "https://registry.npmjs.org/@isaacs/fs-minipass/-/fs-minipass-4.0.1.tgz", @@ -1025,20 +1020,11 @@ "node": ">=18.0.0" } }, - "node_modules/@istanbuljs/schema": { - "version": "0.1.3", - "resolved": "https://registry.npmjs.org/@istanbuljs/schema/-/schema-0.1.3.tgz", - "integrity": "sha512-ZXRY4jNvVgSVQ8DL3LTcakaAtXwTVUxE81hslsyD2AtoXW/wVob10HkOJ1X/pAlcI7D+2YoZKg5do8G/w6RYgA==", - "dev": true, - "license": "MIT", - "engines": { - "node": ">=8" - } - }, "node_modules/@jridgewell/gen-mapping": { "version": "0.3.12", "resolved": "https://registry.npmjs.org/@jridgewell/gen-mapping/-/gen-mapping-0.3.12.tgz", "integrity": "sha512-OuLGC46TjB5BbN1dH8JULVVZY4WTdkF7tV9Ys6wLL1rubZnCMstOhNHueU5bLCrnRuDhKPDM4g6sw4Bel5Gzqg==", + "dev": true, "license": "MIT", "dependencies": { "@jridgewell/sourcemap-codec": "^1.5.0", @@ -1049,6 +1035,7 @@ "version": "2.3.5", "resolved": "https://registry.npmjs.org/@jridgewell/remapping/-/remapping-2.3.5.tgz", "integrity": "sha512-LI9u/+laYG4Ds1TDKSJW2YPrIlcVYOwi2fUC6xB43lueCjgxV4lffOCZCtYFiH6TNOX+tQKXx97T4IKHbhyHEQ==", + "dev": true, "license": "MIT", "dependencies": { "@jridgewell/gen-mapping": "^0.3.5", @@ -1059,21 +1046,24 @@ "version": "3.1.2", "resolved": "https://registry.npmjs.org/@jridgewell/resolve-uri/-/resolve-uri-3.1.2.tgz", "integrity": "sha512-bRISgCIjP20/tbWSPWMEi54QVPRZExkuD9lJL+UIxUKtwVJA8wW1Trb1jMs1RFXo1CBTNZ/5hpC9QvmKWdopKw==", + "dev": true, "license": "MIT", "engines": { "node": ">=6.0.0" } }, "node_modules/@jridgewell/sourcemap-codec": { - "version": "1.5.4", - "resolved": "https://registry.npmjs.org/@jridgewell/sourcemap-codec/-/sourcemap-codec-1.5.4.tgz", - "integrity": "sha512-VT2+G1VQs/9oz078bLrYbecdZKs912zQlkelYpuf+SXF+QvZDYJlbx/LSx+meSAwdDFnF8FVXW92AVjjkVmgFw==", + "version": "1.5.5", + "resolved": "https://registry.npmjs.org/@jridgewell/sourcemap-codec/-/sourcemap-codec-1.5.5.tgz", + "integrity": "sha512-cYQ9310grqxueWbl+WuIUIaiUaDcj7WOq5fVhEljNVgRfOUhY9fy2zTvfoqWsnebh8Sl70VScFbICvJnLKB0Og==", + "dev": true, "license": "MIT" }, "node_modules/@jridgewell/trace-mapping": { "version": "0.3.31", "resolved": "https://registry.npmjs.org/@jridgewell/trace-mapping/-/trace-mapping-0.3.31.tgz", "integrity": "sha512-zzNR+SdQSDJzc8joaeP8QQoCQr8NuYx2dIIytl1QeBEZHJ9uW6hebsrYgbz8hJwUQao3TWCMtmfV8Nu1twOLAw==", + "dev": true, "license": "MIT", "dependencies": { "@jridgewell/resolve-uri": "^3.1.0", @@ -1112,6 +1102,7 @@ "version": "1.1.1", "resolved": "https://registry.npmjs.org/@mermaid-js/parser/-/parser-1.1.1.tgz", "integrity": "sha512-VuHdsYMK1bT6X2JbcAaWAhugTRvRBRyuZgd+c22swUeI9g/ntaxF7CY7dYarhZovofCbUNO0G7JesfmNtjYOCw==", + "dev": true, "license": "MIT", "dependencies": { "@chevrotain/types": "~11.1.1" @@ -1121,6 +1112,7 @@ "version": "1.26.0", "resolved": "https://registry.npmjs.org/@modelcontextprotocol/sdk/-/sdk-1.26.0.tgz", "integrity": "sha512-Y5RmPncpiDtTXDbLKswIJzTqu2hyBKxTNsgKqKclDbhIgg1wgtf1fRuvxgTnRfcnxtvvgbIEcqUOzZrJ6iSReg==", + "dev": true, "license": "MIT", "dependencies": { "@hono/node-server": "^1.19.9", @@ -1161,6 +1153,7 @@ "version": "8.18.0", "resolved": "https://registry.npmjs.org/ajv/-/ajv-8.18.0.tgz", "integrity": "sha512-PlXPeEWMXMZ7sPYOHqmDyCJzcfNrUr3fGNKtezX14ykXOEIvyK81d+qydx89KY5O71FKMPaQ2vBfBFI5NHR63A==", + "dev": true, "license": "MIT", "dependencies": { "fast-deep-equal": "^3.1.3", @@ -1177,12 +1170,14 @@ "version": "1.0.0", "resolved": "https://registry.npmjs.org/json-schema-traverse/-/json-schema-traverse-1.0.0.tgz", "integrity": "sha512-NM8/P9n3XjXhIZn1lLhkFaACTOURQXjWhV4BA/RnOv8xvgqtqpAX9IO4mRQxSx1Rlo4tqzeqb0sOlruaOy3dug==", + "dev": true, "license": "MIT" }, "node_modules/@napi-rs/canvas": { "version": "0.1.76", "resolved": "https://registry.npmjs.org/@napi-rs/canvas/-/canvas-0.1.76.tgz", "integrity": "sha512-YIk5okeNN53GzjvWmAyCQFE9xrLeQXzYpudX4TiLvqaz9SqXgIgxIuKPe4DKyB5nccsQMIev7JGKTzZaN5rFdw==", + "dev": true, "license": "MIT", "optional": true, "workspaces": [ @@ -1211,6 +1206,7 @@ "cpu": [ "arm64" ], + "dev": true, "license": "MIT", "optional": true, "os": [ @@ -1227,6 +1223,7 @@ "cpu": [ "arm64" ], + "dev": true, "license": "MIT", "optional": true, "os": [ @@ -1243,6 +1240,7 @@ "cpu": [ "x64" ], + "dev": true, "license": "MIT", "optional": true, "os": [ @@ -1259,6 +1257,7 @@ "cpu": [ "arm" ], + "dev": true, "license": "MIT", "optional": true, "os": [ @@ -1275,6 +1274,7 @@ "cpu": [ "arm64" ], + "dev": true, "license": "MIT", "optional": true, "os": [ @@ -1291,6 +1291,7 @@ "cpu": [ "arm64" ], + "dev": true, "license": "MIT", "optional": true, "os": [ @@ -1307,6 +1308,7 @@ "cpu": [ "riscv64" ], + "dev": true, "license": "MIT", "optional": true, "os": [ @@ -1323,6 +1325,7 @@ "cpu": [ "x64" ], + "dev": true, "license": "MIT", "optional": true, "os": [ @@ -1339,6 +1342,7 @@ "cpu": [ "x64" ], + "dev": true, "license": "MIT", "optional": true, "os": [ @@ -1355,6 +1359,7 @@ "cpu": [ "x64" ], + "dev": true, "license": "MIT", "optional": true, "os": [ @@ -1695,17 +1700,6 @@ "node": ">=0.10" } }, - "node_modules/@pkgjs/parseargs": { - "version": "0.11.0", - "resolved": "https://registry.npmjs.org/@pkgjs/parseargs/-/parseargs-0.11.0.tgz", - "integrity": "sha512-+1VkjdD0QBLPodGrJUeqarH8VAIvQODIbwh9XpP5Syisf7YoQgsJKPNFoqqLQlu+VQ/tVSshMR6loPMn8U+dPg==", - "dev": true, - "license": "MIT", - "optional": true, - "engines": { - "node": ">=14" - } - }, "node_modules/@playwright/test": { "version": "1.56.1", "resolved": "https://registry.npmjs.org/@playwright/test/-/test-1.56.1.tgz", @@ -2080,9 +2074,9 @@ ] }, "node_modules/@standard-schema/spec": { - "version": "1.0.0", - "resolved": "https://registry.npmjs.org/@standard-schema/spec/-/spec-1.0.0.tgz", - "integrity": "sha512-m2bOd0f2RT9k8QJx1JN85cZYyH1RqFBdlwtkSlf4tBDYLCiiZnv1fIIwacK6cqwXavOydf0NPToMQgpKq+dVlA==", + "version": "1.1.0", + "resolved": "https://registry.npmjs.org/@standard-schema/spec/-/spec-1.1.0.tgz", + "integrity": "sha512-l2aFy5jALhniG5HgqrD6jXLi/rUWrKvqN/qJx6yoJsgKhblVd+iqqU4RCXavm/jPityDo5TCvKMnpjKnOriy0w==", "dev": true, "license": "MIT" }, @@ -2352,6 +2346,7 @@ "version": "1.0.5", "resolved": "https://registry.npmjs.org/@sveltejs/acorn-typescript/-/acorn-typescript-1.0.5.tgz", "integrity": "sha512-IwQk4yfwLdibDlrXVE04jTZYlLnwsTT2PIOQQGNLWfjavGifnk1JD1LcZjZaBTRcxZu2FfPfNLOE04DSu9lqtQ==", + "dev": true, "license": "MIT", "peerDependencies": { "acorn": "^8.9.0" @@ -2825,19 +2820,20 @@ } }, "node_modules/@testing-library/dom": { - "version": "10.4.0", - "resolved": "https://registry.npmjs.org/@testing-library/dom/-/dom-10.4.0.tgz", - "integrity": "sha512-pemlzrSESWbdAloYml3bAJMEfNh1Z7EduzqPKprCH5S341frlpYnUEW0H72dLxa6IsYr+mPno20GiSm+h9dEdQ==", + "version": "10.4.1", + "resolved": "https://registry.npmjs.org/@testing-library/dom/-/dom-10.4.1.tgz", + "integrity": "sha512-o4PXJQidqJl82ckFaXUeoAW+XysPLauYI43Abki5hABd853iMhitooc6znOnczgbTYmEP6U6/y1ZyKAIsvMKGg==", "dev": true, "license": "MIT", + "peer": true, "dependencies": { "@babel/code-frame": "^7.10.4", "@babel/runtime": "^7.12.5", "@types/aria-query": "^5.0.1", "aria-query": "5.3.0", - "chalk": "^4.1.0", "dom-accessibility-api": "^0.5.9", "lz-string": "^1.5.0", + "picocolors": "1.1.1", "pretty-format": "^27.0.2" }, "engines": { @@ -2871,6 +2867,19 @@ "dev": true, "license": "MIT" }, + "node_modules/@testing-library/svelte-core": { + "version": "1.0.0", + "resolved": "https://registry.npmjs.org/@testing-library/svelte-core/-/svelte-core-1.0.0.tgz", + "integrity": "sha512-VkUePoLV6oOYwSUvX6ShA8KLnJqZiYMIbP2JW2t0GLWLkJxKGvuH5qrrZBV/X7cXFnLGuFQEC7RheYiZOW68KQ==", + "dev": true, + "license": "MIT", + "engines": { + "node": ">=16" + }, + "peerDependencies": { + "svelte": "^3 || ^4 || ^5 || ^5.0.0-next.0" + } + }, "node_modules/@testing-library/user-event": { "version": "14.6.1", "resolved": "https://registry.npmjs.org/@testing-library/user-event/-/user-event-14.6.1.tgz", @@ -2890,7 +2899,8 @@ "resolved": "https://registry.npmjs.org/@types/aria-query/-/aria-query-5.0.4.tgz", "integrity": "sha512-rfT93uj5s0PRL7EzccGMs3brplhcrghnDoV26NqKhCAS1hVo+WdNsPvE/yb6ilfr5hi2MEk6d5EWJTKdxg8jVw==", "dev": true, - "license": "MIT" + "license": "MIT", + "peer": true }, "node_modules/@types/chai": { "version": "5.2.2", @@ -2913,6 +2923,7 @@ "version": "7.4.3", "resolved": "https://registry.npmjs.org/@types/d3/-/d3-7.4.3.tgz", "integrity": "sha512-lZXZ9ckh5R8uiFVt8ogUNf+pIrK4EsWrx2Np75WvF/eTpJ0FMHNhjXk8CKEx/+gpHbNQyJWehbFaTvqmHWB3ww==", + "dev": true, "license": "MIT", "dependencies": { "@types/d3-array": "*", @@ -2951,12 +2962,14 @@ "version": "3.2.2", "resolved": "https://registry.npmjs.org/@types/d3-array/-/d3-array-3.2.2.tgz", "integrity": "sha512-hOLWVbm7uRza0BYXpIIW5pxfrKe0W+D5lrFiAEYR+pb6w3N2SwSMaJbXdUfSEv+dT4MfHBLtn5js0LAWaO6otw==", + "dev": true, "license": "MIT" }, "node_modules/@types/d3-axis": { "version": "3.0.6", "resolved": "https://registry.npmjs.org/@types/d3-axis/-/d3-axis-3.0.6.tgz", "integrity": "sha512-pYeijfZuBd87T0hGn0FO1vQ/cgLk6E1ALJjfkC0oJ8cbwkZl3TpgS8bVBLZN+2jjGgg38epgxb2zmoGtSfvgMw==", + "dev": true, "license": "MIT", "dependencies": { "@types/d3-selection": "*" @@ -2966,6 +2979,7 @@ "version": "3.0.6", "resolved": "https://registry.npmjs.org/@types/d3-brush/-/d3-brush-3.0.6.tgz", "integrity": "sha512-nH60IZNNxEcrh6L1ZSMNA28rj27ut/2ZmI3r96Zd+1jrZD++zD3LsMIjWlvg4AYrHn/Pqz4CF3veCxGjtbqt7A==", + "dev": true, "license": "MIT", "dependencies": { "@types/d3-selection": "*" @@ -2975,18 +2989,21 @@ "version": "3.0.6", "resolved": "https://registry.npmjs.org/@types/d3-chord/-/d3-chord-3.0.6.tgz", "integrity": "sha512-LFYWWd8nwfwEmTZG9PfQxd17HbNPksHBiJHaKuY1XeqscXacsS2tyoo6OdRsjf+NQYeB6XrNL3a25E3gH69lcg==", + "dev": true, "license": "MIT" }, "node_modules/@types/d3-color": { "version": "3.1.3", "resolved": "https://registry.npmjs.org/@types/d3-color/-/d3-color-3.1.3.tgz", "integrity": "sha512-iO90scth9WAbmgv7ogoq57O9YpKmFBbmoEoCHDB2xMBY0+/KVrqAaCDyCE16dUspeOvIxFFRI+0sEtqDqy2b4A==", + "dev": true, "license": "MIT" }, "node_modules/@types/d3-contour": { "version": "3.0.6", "resolved": "https://registry.npmjs.org/@types/d3-contour/-/d3-contour-3.0.6.tgz", "integrity": "sha512-BjzLgXGnCWjUSYGfH1cpdo41/hgdWETu4YxpezoztawmqsvCeep+8QGfiY6YbDvfgHz/DkjeIkkZVJavB4a3rg==", + "dev": true, "license": "MIT", "dependencies": { "@types/d3-array": "*", @@ -2997,18 +3014,21 @@ "version": "6.0.4", "resolved": "https://registry.npmjs.org/@types/d3-delaunay/-/d3-delaunay-6.0.4.tgz", "integrity": "sha512-ZMaSKu4THYCU6sV64Lhg6qjf1orxBthaC161plr5KuPHo3CNm8DTHiLw/5Eq2b6TsNP0W0iJrUOFscY6Q450Hw==", + "dev": true, "license": "MIT" }, "node_modules/@types/d3-dispatch": { "version": "3.0.7", "resolved": "https://registry.npmjs.org/@types/d3-dispatch/-/d3-dispatch-3.0.7.tgz", "integrity": "sha512-5o9OIAdKkhN1QItV2oqaE5KMIiXAvDWBDPrD85e58Qlz1c1kI/J0NcqbEG88CoTwJrYe7ntUCVfeUl2UJKbWgA==", + "dev": true, "license": "MIT" }, "node_modules/@types/d3-drag": { "version": "3.0.7", "resolved": "https://registry.npmjs.org/@types/d3-drag/-/d3-drag-3.0.7.tgz", "integrity": "sha512-HE3jVKlzU9AaMazNufooRJ5ZpWmLIoc90A37WU2JMmeq28w1FQqCZswHZ3xR+SuxYftzHq6WU6KJHvqxKzTxxQ==", + "dev": true, "license": "MIT", "dependencies": { "@types/d3-selection": "*" @@ -3018,18 +3038,21 @@ "version": "3.0.7", "resolved": "https://registry.npmjs.org/@types/d3-dsv/-/d3-dsv-3.0.7.tgz", "integrity": "sha512-n6QBF9/+XASqcKK6waudgL0pf/S5XHPPI8APyMLLUHd8NqouBGLsU8MgtO7NINGtPBtk9Kko/W4ea0oAspwh9g==", + "dev": true, "license": "MIT" }, "node_modules/@types/d3-ease": { "version": "3.0.2", "resolved": "https://registry.npmjs.org/@types/d3-ease/-/d3-ease-3.0.2.tgz", "integrity": "sha512-NcV1JjO5oDzoK26oMzbILE6HW7uVXOHLQvHshBUW4UMdZGfiY6v5BeQwh9a9tCzv+CeefZQHJt5SRgK154RtiA==", + "dev": true, "license": "MIT" }, "node_modules/@types/d3-fetch": { "version": "3.0.7", "resolved": "https://registry.npmjs.org/@types/d3-fetch/-/d3-fetch-3.0.7.tgz", "integrity": "sha512-fTAfNmxSb9SOWNB9IoG5c8Hg6R+AzUHDRlsXsDZsNp6sxAEOP0tkP3gKkNSO/qmHPoBFTxNrjDprVHDQDvo5aA==", + "dev": true, "license": "MIT", "dependencies": { "@types/d3-dsv": "*" @@ -3039,18 +3062,21 @@ "version": "3.0.10", "resolved": "https://registry.npmjs.org/@types/d3-force/-/d3-force-3.0.10.tgz", "integrity": "sha512-ZYeSaCF3p73RdOKcjj+swRlZfnYpK1EbaDiYICEEp5Q6sUiqFaFQ9qgoshp5CzIyyb/yD09kD9o2zEltCexlgw==", + "dev": true, "license": "MIT" }, "node_modules/@types/d3-format": { "version": "3.0.4", "resolved": "https://registry.npmjs.org/@types/d3-format/-/d3-format-3.0.4.tgz", "integrity": "sha512-fALi2aI6shfg7vM5KiR1wNJnZ7r6UuggVqtDA+xiEdPZQwy/trcQaHnwShLuLdta2rTymCNpxYTiMZX/e09F4g==", + "dev": true, "license": "MIT" }, "node_modules/@types/d3-geo": { "version": "3.1.0", "resolved": "https://registry.npmjs.org/@types/d3-geo/-/d3-geo-3.1.0.tgz", "integrity": "sha512-856sckF0oP/diXtS4jNsiQw/UuK5fQG8l/a9VVLeSouf1/PPbBE1i1W852zVwKwYCBkFJJB7nCFTbk6UMEXBOQ==", + "dev": true, "license": "MIT", "dependencies": { "@types/geojson": "*" @@ -3060,12 +3086,14 @@ "version": "3.1.7", "resolved": "https://registry.npmjs.org/@types/d3-hierarchy/-/d3-hierarchy-3.1.7.tgz", "integrity": "sha512-tJFtNoYBtRtkNysX1Xq4sxtjK8YgoWUNpIiUee0/jHGRwqvzYxkq0hGVbbOGSz+JgFxxRu4K8nb3YpG3CMARtg==", + "dev": true, "license": "MIT" }, "node_modules/@types/d3-interpolate": { "version": "3.0.4", "resolved": "https://registry.npmjs.org/@types/d3-interpolate/-/d3-interpolate-3.0.4.tgz", "integrity": "sha512-mgLPETlrpVV1YRJIglr4Ez47g7Yxjl1lj7YKsiMCb27VJH9W8NVM6Bb9d8kkpG/uAQS5AmbA48q2IAolKKo1MA==", + "dev": true, "license": "MIT", "dependencies": { "@types/d3-color": "*" @@ -3075,30 +3103,35 @@ "version": "3.1.1", "resolved": "https://registry.npmjs.org/@types/d3-path/-/d3-path-3.1.1.tgz", "integrity": "sha512-VMZBYyQvbGmWyWVea0EHs/BwLgxc+MKi1zLDCONksozI4YJMcTt8ZEuIR4Sb1MMTE8MMW49v0IwI5+b7RmfWlg==", + "dev": true, "license": "MIT" }, "node_modules/@types/d3-polygon": { "version": "3.0.2", "resolved": "https://registry.npmjs.org/@types/d3-polygon/-/d3-polygon-3.0.2.tgz", "integrity": "sha512-ZuWOtMaHCkN9xoeEMr1ubW2nGWsp4nIql+OPQRstu4ypeZ+zk3YKqQT0CXVe/PYqrKpZAi+J9mTs05TKwjXSRA==", + "dev": true, "license": "MIT" }, "node_modules/@types/d3-quadtree": { "version": "3.0.6", "resolved": "https://registry.npmjs.org/@types/d3-quadtree/-/d3-quadtree-3.0.6.tgz", "integrity": "sha512-oUzyO1/Zm6rsxKRHA1vH0NEDG58HrT5icx/azi9MF1TWdtttWl0UIUsjEQBBh+SIkrpd21ZjEv7ptxWys1ncsg==", + "dev": true, "license": "MIT" }, "node_modules/@types/d3-random": { "version": "3.0.3", "resolved": "https://registry.npmjs.org/@types/d3-random/-/d3-random-3.0.3.tgz", "integrity": "sha512-Imagg1vJ3y76Y2ea0871wpabqp613+8/r0mCLEBfdtqC7xMSfj9idOnmBYyMoULfHePJyxMAw3nWhJxzc+LFwQ==", + "dev": true, "license": "MIT" }, "node_modules/@types/d3-scale": { "version": "4.0.9", "resolved": "https://registry.npmjs.org/@types/d3-scale/-/d3-scale-4.0.9.tgz", "integrity": "sha512-dLmtwB8zkAeO/juAMfnV+sItKjlsw2lKdZVVy6LRr0cBmegxSABiLEpGVmSJJ8O08i4+sGR6qQtb6WtuwJdvVw==", + "dev": true, "license": "MIT", "dependencies": { "@types/d3-time": "*" @@ -3108,18 +3141,21 @@ "version": "3.1.0", "resolved": "https://registry.npmjs.org/@types/d3-scale-chromatic/-/d3-scale-chromatic-3.1.0.tgz", "integrity": "sha512-iWMJgwkK7yTRmWqRB5plb1kadXyQ5Sj8V/zYlFGMUBbIPKQScw+Dku9cAAMgJG+z5GYDoMjWGLVOvjghDEFnKQ==", + "dev": true, "license": "MIT" }, "node_modules/@types/d3-selection": { "version": "3.0.11", "resolved": "https://registry.npmjs.org/@types/d3-selection/-/d3-selection-3.0.11.tgz", "integrity": "sha512-bhAXu23DJWsrI45xafYpkQ4NtcKMwWnAC/vKrd2l+nxMFuvOT3XMYTIj2opv8vq8AO5Yh7Qac/nSeP/3zjTK0w==", + "dev": true, "license": "MIT" }, "node_modules/@types/d3-shape": { "version": "3.1.8", "resolved": "https://registry.npmjs.org/@types/d3-shape/-/d3-shape-3.1.8.tgz", "integrity": "sha512-lae0iWfcDeR7qt7rA88BNiqdvPS5pFVPpo5OfjElwNaT2yyekbM0C9vK+yqBqEmHr6lDkRnYNoTBYlAgJa7a4w==", + "dev": true, "license": "MIT", "dependencies": { "@types/d3-path": "*" @@ -3129,24 +3165,28 @@ "version": "3.0.4", "resolved": "https://registry.npmjs.org/@types/d3-time/-/d3-time-3.0.4.tgz", "integrity": "sha512-yuzZug1nkAAaBlBBikKZTgzCeA+k1uy4ZFwWANOfKw5z5LRhV0gNA7gNkKm7HoK+HRN0wX3EkxGk0fpbWhmB7g==", + "dev": true, "license": "MIT" }, "node_modules/@types/d3-time-format": { "version": "4.0.3", "resolved": "https://registry.npmjs.org/@types/d3-time-format/-/d3-time-format-4.0.3.tgz", "integrity": "sha512-5xg9rC+wWL8kdDj153qZcsJ0FWiFt0J5RB6LYUNZjwSnesfblqrI/bJ1wBdJ8OQfncgbJG5+2F+qfqnqyzYxyg==", + "dev": true, "license": "MIT" }, "node_modules/@types/d3-timer": { "version": "3.0.2", "resolved": "https://registry.npmjs.org/@types/d3-timer/-/d3-timer-3.0.2.tgz", "integrity": "sha512-Ps3T8E8dZDam6fUyNiMkekK3XUsaUEik+idO9/YjPtfj2qruF8tFBXS7XhtE4iIXBLxhmLjP3SXpLhVf21I9Lw==", + "dev": true, "license": "MIT" }, "node_modules/@types/d3-transition": { "version": "3.0.9", "resolved": "https://registry.npmjs.org/@types/d3-transition/-/d3-transition-3.0.9.tgz", "integrity": "sha512-uZS5shfxzO3rGlu0cC3bjmMFKsXv+SmZZcgp0KD22ts4uGXp5EVYGzu/0YdwZeKmddhcAccYtREJKkPfXkZuCg==", + "dev": true, "license": "MIT", "dependencies": { "@types/d3-selection": "*" @@ -3156,6 +3196,7 @@ "version": "3.0.8", "resolved": "https://registry.npmjs.org/@types/d3-zoom/-/d3-zoom-3.0.8.tgz", "integrity": "sha512-iqMC4/YlFCSlO8+2Ii1GGGliCAY4XdeG748w5vQUbevlbDu0zSjH/+jojorQVBK/se0j6DUFNPBGSqD3YWYnDw==", + "dev": true, "license": "MIT", "dependencies": { "@types/d3-interpolate": "*", @@ -3166,6 +3207,7 @@ "version": "4.1.12", "resolved": "https://registry.npmjs.org/@types/debug/-/debug-4.1.12.tgz", "integrity": "sha512-vIChWdVG3LG1SMxEvI/AK+FWJthlrqlTu7fbrlywTkkaONwk/UAGaULXRlf8vkzFBLVm0zkMdCquhL5aOjhXPQ==", + "dev": true, "license": "MIT", "dependencies": { "@types/ms": "*" @@ -3182,18 +3224,21 @@ "version": "1.0.8", "resolved": "https://registry.npmjs.org/@types/estree/-/estree-1.0.8.tgz", "integrity": "sha512-dWHzHa2WqEXI/O1E9OjrocMTKJl2mSrEolh1Iomrv6U+JuNwaHXsXx9bLu5gG7BUWFIN0skIQJQ/L1rIex4X6w==", + "dev": true, "license": "MIT" }, "node_modules/@types/geojson": { "version": "7946.0.16", "resolved": "https://registry.npmjs.org/@types/geojson/-/geojson-7946.0.16.tgz", "integrity": "sha512-6C8nqWur3j98U6+lXDfTUWIfgvZU+EumvpHKcYjujKH7woYyLj2sUmff0tRhrqM7BohUw7Pz3ZB1jj2gW9Fvmg==", + "dev": true, "license": "MIT" }, "node_modules/@types/hast": { "version": "3.0.4", "resolved": "https://registry.npmjs.org/@types/hast/-/hast-3.0.4.tgz", "integrity": "sha512-WPs+bbQw5aCj+x6laNGWLH3wviHtoCv/P3+otBhbOhJgG8qtpdAMlTCxLtsTWA7LH1Oh/bFCHsBn0TPS5m30EQ==", + "dev": true, "license": "MIT", "dependencies": { "@types/unist": "*" @@ -3217,6 +3262,7 @@ "version": "4.0.4", "resolved": "https://registry.npmjs.org/@types/mdast/-/mdast-4.0.4.tgz", "integrity": "sha512-kGaNbPh1k7AFzgpud/gMdvIm5xuECykRR+JnWKQno9TAXVa6WIVCGTPvYGekIDL4uwCZQSYbUxNBSb1aUo79oA==", + "dev": true, "license": "MIT", "dependencies": { "@types/unist": "*" @@ -3233,6 +3279,7 @@ "version": "2.1.0", "resolved": "https://registry.npmjs.org/@types/ms/-/ms-2.1.0.tgz", "integrity": "sha512-GsCCIZDE/p3i96vtEqx+7dBUGXrc7zeSK3wwPHIaRThS+9OhWIXRqzs4d6k1SVU8g91DrNRWxWUGhp5KXQb2VA==", + "dev": true, "license": "MIT" }, "node_modules/@types/node": { @@ -3246,26 +3293,28 @@ } }, "node_modules/@types/react": { - "version": "19.1.8", - "resolved": "https://registry.npmjs.org/@types/react/-/react-19.1.8.tgz", - "integrity": "sha512-AwAfQ2Wa5bCx9WP8nZL2uMZWod7J7/JSplxbTmBQ5ms6QpqNYm672H0Vu9ZVKVngQ+ii4R/byguVEUZQyeg44g==", + "version": "19.2.16", + "resolved": "https://registry.npmjs.org/@types/react/-/react-19.2.16.tgz", + "integrity": "sha512-esJiCAnl0kfpNdE69f3So4WJUXy95dLZydX0KwK46riIHDzHM7O9Vtf9xCHW0PXIqvgqNrswl522kA/5yx+F4w==", "dev": true, "license": "MIT", "peer": true, "dependencies": { - "csstype": "^3.0.2" + "csstype": "^3.2.2" } }, "node_modules/@types/trusted-types": { "version": "2.0.7", "resolved": "https://registry.npmjs.org/@types/trusted-types/-/trusted-types-2.0.7.tgz", "integrity": "sha512-ScaPdn1dQczgbl0QFTeTOmVHFULt394XJgOQNoyVhZ6r2vLnMLJfBPd53SB52T/3G36VI1/g2MZaX0cwDuXsfw==", + "dev": true, "license": "MIT" }, "node_modules/@types/unist": { "version": "2.0.11", "resolved": "https://registry.npmjs.org/@types/unist/-/unist-2.0.11.tgz", "integrity": "sha512-CmBKiL6NNo/OqgmMn95Fk9Whlp2mtvIv+KNpQKN2F4SjvrEesubTRWGYSg+BnWZOnlCaSTU1sMpsBOzgbYhnsA==", + "dev": true, "license": "MIT" }, "node_modules/@typescript-eslint/eslint-plugin": { @@ -3418,6 +3467,7 @@ "version": "8.56.0", "resolved": "https://registry.npmjs.org/@typescript-eslint/types/-/types-8.56.0.tgz", "integrity": "sha512-DBsLPs3GsWhX5HylbP9HNG15U0bnwut55Lx12bHB9MpXxQ+R5GC8MwQe+N1UFXxAeQDvEsEDY6ZYwX03K7Z6HQ==", + "dev": true, "license": "MIT", "engines": { "node": "^18.18.0 || ^20.9.0 || >=21.1.0" @@ -3540,12 +3590,14 @@ "version": "1.3.0", "resolved": "https://registry.npmjs.org/@ungap/structured-clone/-/structured-clone-1.3.0.tgz", "integrity": "sha512-WmoN8qaIAo7WTYWbAZuG8PYEhn5fkz7dZrqTBZ7dtt//lL2Gwms1IcnQ5yHqjDfX8Ft5j4YzDM23f87zBfDe9g==", + "dev": true, "license": "ISC" }, "node_modules/@upsetjs/venn.js": { "version": "2.0.0", "resolved": "https://registry.npmjs.org/@upsetjs/venn.js/-/venn.js-2.0.0.tgz", "integrity": "sha512-WbBhLrooyePuQ1VZxrJjtLvTc4NVfpOyKx0sKqioq9bX1C1m7Jgykkn8gLrtwumBioXIqam8DLxp88Adbue6Hw==", + "dev": true, "license": "MIT", "optionalDependencies": { "d3-selection": "^3.0.0", @@ -3553,68 +3605,124 @@ } }, "node_modules/@vitest/browser": { - "version": "3.2.4", - "resolved": "https://registry.npmjs.org/@vitest/browser/-/browser-3.2.4.tgz", - "integrity": "sha512-tJxiPrWmzH8a+w9nLKlQMzAKX/7VjFs50MWgcAj7p9XQ7AQ9/35fByFYptgPELyLw+0aixTnC4pUWV+APcZ/kw==", + "version": "4.1.8", + "resolved": "https://registry.npmjs.org/@vitest/browser/-/browser-4.1.8.tgz", + "integrity": "sha512-u21VzX07HzlJYpFgkxmjEXar/tG2UqWGgyGG/46SrrPc7rSdCTPw5vuowopO9CIqF8UCUQzDFdbVnNpw6N0BfQ==", "dev": true, "license": "MIT", "dependencies": { - "@testing-library/dom": "^10.4.0", - "@testing-library/user-event": "^14.6.1", - "@vitest/mocker": "3.2.4", - "@vitest/utils": "3.2.4", - "magic-string": "^0.30.17", - "sirv": "^3.0.1", - "tinyrainbow": "^2.0.0", - "ws": "^8.18.2" + "@blazediff/core": "1.9.1", + "@vitest/mocker": "4.1.8", + "@vitest/utils": "4.1.8", + "magic-string": "^0.30.21", + "pngjs": "^7.0.0", + "sirv": "^3.0.2", + "tinyrainbow": "^3.1.0", + "ws": "^8.19.0" + }, + "funding": { + "url": "https://opencollective.com/vitest" + }, + "peerDependencies": { + "vitest": "4.1.8" + } + }, + "node_modules/@vitest/browser-playwright": { + "version": "4.1.8", + "resolved": "https://registry.npmjs.org/@vitest/browser-playwright/-/browser-playwright-4.1.8.tgz", + "integrity": "sha512-SR7FqgegaexEg73xvf3ArtygXegagMdXnL0EZMpxrWvvhQxvicD/E8p0ib0J91riPRtQUViyh67Xjw3NqvyhVg==", + "dev": true, + "license": "MIT", + "dependencies": { + "@vitest/browser": "4.1.8", + "@vitest/mocker": "4.1.8", + "tinyrainbow": "^3.1.0" }, "funding": { "url": "https://opencollective.com/vitest" }, "peerDependencies": { "playwright": "*", - "vitest": "3.2.4", - "webdriverio": "^7.0.0 || ^8.0.0 || ^9.0.0" + "vitest": "4.1.8" }, "peerDependenciesMeta": { "playwright": { - "optional": true - }, - "safaridriver": { - "optional": true - }, - "webdriverio": { - "optional": true + "optional": false } } }, + "node_modules/@vitest/browser-playwright/node_modules/tinyrainbow": { + "version": "3.1.0", + "resolved": "https://registry.npmjs.org/tinyrainbow/-/tinyrainbow-3.1.0.tgz", + "integrity": "sha512-Bf+ILmBgretUrdJxzXM0SgXLZ3XfiaUuOj/IKQHuTXip+05Xn+uyEYdVg0kYDipTBcLrCVyUzAPz7QmArb0mmw==", + "dev": true, + "license": "MIT", + "engines": { + "node": ">=14.0.0" + } + }, + "node_modules/@vitest/browser/node_modules/@vitest/pretty-format": { + "version": "4.1.8", + "resolved": "https://registry.npmjs.org/@vitest/pretty-format/-/pretty-format-4.1.8.tgz", + "integrity": "sha512-9GasEBxpZ1VYIpqHf/0+YGg121uSNwCKOJqIrTwWP/TB7DmFCiaBpNl3aPZzoLWfWkuqhbH8vJIVobZkvdo2cA==", + "dev": true, + "license": "MIT", + "dependencies": { + "tinyrainbow": "^3.1.0" + }, + "funding": { + "url": "https://opencollective.com/vitest" + } + }, + "node_modules/@vitest/browser/node_modules/@vitest/utils": { + "version": "4.1.8", + "resolved": "https://registry.npmjs.org/@vitest/utils/-/utils-4.1.8.tgz", + "integrity": "sha512-uOJamYALNhfJ6iolExyQM40yIQwDqYnkKtQ5VCiSe17E33H0aQ/u+1GlRuz4LZBk6Mm3sg90G9hEbmEt37C1Zg==", + "dev": true, + "license": "MIT", + "dependencies": { + "@vitest/pretty-format": "4.1.8", + "convert-source-map": "^2.0.0", + "tinyrainbow": "^3.1.0" + }, + "funding": { + "url": "https://opencollective.com/vitest" + } + }, + "node_modules/@vitest/browser/node_modules/tinyrainbow": { + "version": "3.1.0", + "resolved": "https://registry.npmjs.org/tinyrainbow/-/tinyrainbow-3.1.0.tgz", + "integrity": "sha512-Bf+ILmBgretUrdJxzXM0SgXLZ3XfiaUuOj/IKQHuTXip+05Xn+uyEYdVg0kYDipTBcLrCVyUzAPz7QmArb0mmw==", + "dev": true, + "license": "MIT", + "engines": { + "node": ">=14.0.0" + } + }, "node_modules/@vitest/coverage-v8": { - "version": "3.2.4", - "resolved": "https://registry.npmjs.org/@vitest/coverage-v8/-/coverage-v8-3.2.4.tgz", - "integrity": "sha512-EyF9SXU6kS5Ku/U82E259WSnvg6c8KTjppUncuNdm5QHpe17mwREHnjDzozC8x9MZ0xfBUFSaLkRv4TMA75ALQ==", + "version": "4.1.8", + "resolved": "https://registry.npmjs.org/@vitest/coverage-v8/-/coverage-v8-4.1.8.tgz", + "integrity": "sha512-lt3kovsyHwYe00wq4D1ti0Z974fWj4NLp6siqiyEufUpyFwK9Yhi7rBhac9JL5aA0zoMrJqc4vYPZRUnI7l7nw==", "dev": true, "license": "MIT", "dependencies": { - "@ampproject/remapping": "^2.3.0", "@bcoe/v8-coverage": "^1.0.2", - "ast-v8-to-istanbul": "^0.3.3", - "debug": "^4.4.1", + "@vitest/utils": "4.1.8", + "ast-v8-to-istanbul": "^1.0.0", "istanbul-lib-coverage": "^3.2.2", "istanbul-lib-report": "^3.0.1", - "istanbul-lib-source-maps": "^5.0.6", - "istanbul-reports": "^3.1.7", - "magic-string": "^0.30.17", - "magicast": "^0.3.5", - "std-env": "^3.9.0", - "test-exclude": "^7.0.1", - "tinyrainbow": "^2.0.0" + "istanbul-reports": "^3.2.0", + "magicast": "^0.5.2", + "obug": "^2.1.1", + "std-env": "^4.0.0-rc.1", + "tinyrainbow": "^3.1.0" }, "funding": { "url": "https://opencollective.com/vitest" }, "peerDependencies": { - "@vitest/browser": "3.2.4", - "vitest": "3.2.4" + "@vitest/browser": "4.1.8", + "vitest": "4.1.8" }, "peerDependenciesMeta": { "@vitest/browser": { @@ -3622,6 +3730,44 @@ } } }, + "node_modules/@vitest/coverage-v8/node_modules/@vitest/pretty-format": { + "version": "4.1.8", + "resolved": "https://registry.npmjs.org/@vitest/pretty-format/-/pretty-format-4.1.8.tgz", + "integrity": "sha512-9GasEBxpZ1VYIpqHf/0+YGg121uSNwCKOJqIrTwWP/TB7DmFCiaBpNl3aPZzoLWfWkuqhbH8vJIVobZkvdo2cA==", + "dev": true, + "license": "MIT", + "dependencies": { + "tinyrainbow": "^3.1.0" + }, + "funding": { + "url": "https://opencollective.com/vitest" + } + }, + "node_modules/@vitest/coverage-v8/node_modules/@vitest/utils": { + "version": "4.1.8", + "resolved": "https://registry.npmjs.org/@vitest/utils/-/utils-4.1.8.tgz", + "integrity": "sha512-uOJamYALNhfJ6iolExyQM40yIQwDqYnkKtQ5VCiSe17E33H0aQ/u+1GlRuz4LZBk6Mm3sg90G9hEbmEt37C1Zg==", + "dev": true, + "license": "MIT", + "dependencies": { + "@vitest/pretty-format": "4.1.8", + "convert-source-map": "^2.0.0", + "tinyrainbow": "^3.1.0" + }, + "funding": { + "url": "https://opencollective.com/vitest" + } + }, + "node_modules/@vitest/coverage-v8/node_modules/tinyrainbow": { + "version": "3.1.0", + "resolved": "https://registry.npmjs.org/tinyrainbow/-/tinyrainbow-3.1.0.tgz", + "integrity": "sha512-Bf+ILmBgretUrdJxzXM0SgXLZ3XfiaUuOj/IKQHuTXip+05Xn+uyEYdVg0kYDipTBcLrCVyUzAPz7QmArb0mmw==", + "dev": true, + "license": "MIT", + "engines": { + "node": ">=14.0.0" + } + }, "node_modules/@vitest/expect": { "version": "3.2.4", "resolved": "https://registry.npmjs.org/@vitest/expect/-/expect-3.2.4.tgz", @@ -3640,22 +3786,22 @@ } }, "node_modules/@vitest/mocker": { - "version": "3.2.4", - "resolved": "https://registry.npmjs.org/@vitest/mocker/-/mocker-3.2.4.tgz", - "integrity": "sha512-46ryTE9RZO/rfDd7pEqFl7etuyzekzEhUbTW3BvmeO/BcCMEgq59BKhek3dXDWgAj4oMK6OZi+vRr1wPW6qjEQ==", + "version": "4.1.8", + "resolved": "https://registry.npmjs.org/@vitest/mocker/-/mocker-4.1.8.tgz", + "integrity": "sha512-LEiN/xe4OSIbKe9HQIp5OC24agGD9J5CnmMgsLohVVoOPWL9a2sBoR6VBx43jQZb7Kr1l4RCuyCJzcAa0+dojw==", "dev": true, "license": "MIT", "dependencies": { - "@vitest/spy": "3.2.4", + "@vitest/spy": "4.1.8", "estree-walker": "^3.0.3", - "magic-string": "^0.30.17" + "magic-string": "^0.30.21" }, "funding": { "url": "https://opencollective.com/vitest" }, "peerDependencies": { "msw": "^2.4.9", - "vite": "^5.0.0 || ^6.0.0 || ^7.0.0-0" + "vite": "^6.0.0 || ^7.0.0 || ^8.0.0" }, "peerDependenciesMeta": { "msw": { @@ -3666,6 +3812,16 @@ } } }, + "node_modules/@vitest/mocker/node_modules/@vitest/spy": { + "version": "4.1.8", + "resolved": "https://registry.npmjs.org/@vitest/spy/-/spy-4.1.8.tgz", + "integrity": "sha512-6EevtBp6OZOPF7bmz36HrGMeP3txgVSrgebWxHOafDXGkhIzfXK14f8KF6MuFfgXXUeHxmpD3BQxkV00/3s5mA==", + "dev": true, + "license": "MIT", + "funding": { + "url": "https://opencollective.com/vitest" + } + }, "node_modules/@vitest/pretty-format": { "version": "3.2.4", "resolved": "https://registry.npmjs.org/@vitest/pretty-format/-/pretty-format-3.2.4.tgz", @@ -3680,71 +3836,148 @@ } }, "node_modules/@vitest/runner": { - "version": "3.2.4", - "resolved": "https://registry.npmjs.org/@vitest/runner/-/runner-3.2.4.tgz", - "integrity": "sha512-oukfKT9Mk41LreEW09vt45f8wx7DordoWUZMYdY/cyAk7w5TWkTRCNZYF7sX7n2wB7jyGAl74OxgwhPgKaqDMQ==", + "version": "4.1.8", + "resolved": "https://registry.npmjs.org/@vitest/runner/-/runner-4.1.8.tgz", + "integrity": "sha512-EmVxeBAfMJvycdjd6Hm+RbFBbA9fKvo0Kx37hNpBYoYeavH3RNsBXWDooR1mgD52dCrxIIuP7UotpfiwOikvcg==", "dev": true, "license": "MIT", "dependencies": { - "@vitest/utils": "3.2.4", - "pathe": "^2.0.3", - "strip-literal": "^3.0.0" + "@vitest/utils": "4.1.8", + "pathe": "^2.0.3" }, "funding": { "url": "https://opencollective.com/vitest" } }, - "node_modules/@vitest/snapshot": { - "version": "3.2.4", - "resolved": "https://registry.npmjs.org/@vitest/snapshot/-/snapshot-3.2.4.tgz", - "integrity": "sha512-dEYtS7qQP2CjU27QBC5oUOxLE/v5eLkGqPE0ZKEIDGMs4vKWe7IjgLOeauHsR0D5YuuycGRO5oSRXnwnmA78fQ==", + "node_modules/@vitest/runner/node_modules/@vitest/pretty-format": { + "version": "4.1.8", + "resolved": "https://registry.npmjs.org/@vitest/pretty-format/-/pretty-format-4.1.8.tgz", + "integrity": "sha512-9GasEBxpZ1VYIpqHf/0+YGg121uSNwCKOJqIrTwWP/TB7DmFCiaBpNl3aPZzoLWfWkuqhbH8vJIVobZkvdo2cA==", "dev": true, "license": "MIT", "dependencies": { - "@vitest/pretty-format": "3.2.4", - "magic-string": "^0.30.17", - "pathe": "^2.0.3" + "tinyrainbow": "^3.1.0" }, "funding": { "url": "https://opencollective.com/vitest" } }, - "node_modules/@vitest/spy": { - "version": "3.2.4", - "resolved": "https://registry.npmjs.org/@vitest/spy/-/spy-3.2.4.tgz", - "integrity": "sha512-vAfasCOe6AIK70iP5UD11Ac4siNUNJ9i/9PZ3NKx07sG6sUxeag1LWdNrMWeKKYBLlzuK+Gn65Yd5nyL6ds+nw==", + "node_modules/@vitest/runner/node_modules/@vitest/utils": { + "version": "4.1.8", + "resolved": "https://registry.npmjs.org/@vitest/utils/-/utils-4.1.8.tgz", + "integrity": "sha512-uOJamYALNhfJ6iolExyQM40yIQwDqYnkKtQ5VCiSe17E33H0aQ/u+1GlRuz4LZBk6Mm3sg90G9hEbmEt37C1Zg==", "dev": true, "license": "MIT", "dependencies": { - "tinyspy": "^4.0.3" + "@vitest/pretty-format": "4.1.8", + "convert-source-map": "^2.0.0", + "tinyrainbow": "^3.1.0" }, "funding": { "url": "https://opencollective.com/vitest" } }, - "node_modules/@vitest/utils": { - "version": "3.2.4", - "resolved": "https://registry.npmjs.org/@vitest/utils/-/utils-3.2.4.tgz", - "integrity": "sha512-fB2V0JFrQSMsCo9HiSq3Ezpdv4iYaXRG1Sx8edX3MwxfyNn83mKiGzOcH+Fkxt4MHxr3y42fQi1oeAInqgX2QA==", + "node_modules/@vitest/runner/node_modules/tinyrainbow": { + "version": "3.1.0", + "resolved": "https://registry.npmjs.org/tinyrainbow/-/tinyrainbow-3.1.0.tgz", + "integrity": "sha512-Bf+ILmBgretUrdJxzXM0SgXLZ3XfiaUuOj/IKQHuTXip+05Xn+uyEYdVg0kYDipTBcLrCVyUzAPz7QmArb0mmw==", + "dev": true, + "license": "MIT", + "engines": { + "node": ">=14.0.0" + } + }, + "node_modules/@vitest/snapshot": { + "version": "4.1.8", + "resolved": "https://registry.npmjs.org/@vitest/snapshot/-/snapshot-4.1.8.tgz", + "integrity": "sha512-acfZboRmAIf05DEKcBQy33VXojFJjtUdLyo7oOmV9kebb2xdU01UknNiPuPZoJZQyO7DF0gZdTGTpeAzET9QPQ==", "dev": true, "license": "MIT", "dependencies": { - "@vitest/pretty-format": "3.2.4", - "loupe": "^3.1.4", - "tinyrainbow": "^2.0.0" + "@vitest/pretty-format": "4.1.8", + "@vitest/utils": "4.1.8", + "magic-string": "^0.30.21", + "pathe": "^2.0.3" }, "funding": { "url": "https://opencollective.com/vitest" } }, - "node_modules/accepts": { - "version": "2.0.0", - "resolved": "https://registry.npmjs.org/accepts/-/accepts-2.0.0.tgz", - "integrity": "sha512-5cvg6CtKwfgdmVqY1WIiXKc3Q1bkRqGLi+2W/6ao+6Y7gu/RCwRuAhGEzh5B4KlszSuTLgZYuqFqo5bImjNKng==", + "node_modules/@vitest/snapshot/node_modules/@vitest/pretty-format": { + "version": "4.1.8", + "resolved": "https://registry.npmjs.org/@vitest/pretty-format/-/pretty-format-4.1.8.tgz", + "integrity": "sha512-9GasEBxpZ1VYIpqHf/0+YGg121uSNwCKOJqIrTwWP/TB7DmFCiaBpNl3aPZzoLWfWkuqhbH8vJIVobZkvdo2cA==", + "dev": true, "license": "MIT", "dependencies": { - "mime-types": "^3.0.0", - "negotiator": "^1.0.0" + "tinyrainbow": "^3.1.0" + }, + "funding": { + "url": "https://opencollective.com/vitest" + } + }, + "node_modules/@vitest/snapshot/node_modules/@vitest/utils": { + "version": "4.1.8", + "resolved": "https://registry.npmjs.org/@vitest/utils/-/utils-4.1.8.tgz", + "integrity": "sha512-uOJamYALNhfJ6iolExyQM40yIQwDqYnkKtQ5VCiSe17E33H0aQ/u+1GlRuz4LZBk6Mm3sg90G9hEbmEt37C1Zg==", + "dev": true, + "license": "MIT", + "dependencies": { + "@vitest/pretty-format": "4.1.8", + "convert-source-map": "^2.0.0", + "tinyrainbow": "^3.1.0" + }, + "funding": { + "url": "https://opencollective.com/vitest" + } + }, + "node_modules/@vitest/snapshot/node_modules/tinyrainbow": { + "version": "3.1.0", + "resolved": "https://registry.npmjs.org/tinyrainbow/-/tinyrainbow-3.1.0.tgz", + "integrity": "sha512-Bf+ILmBgretUrdJxzXM0SgXLZ3XfiaUuOj/IKQHuTXip+05Xn+uyEYdVg0kYDipTBcLrCVyUzAPz7QmArb0mmw==", + "dev": true, + "license": "MIT", + "engines": { + "node": ">=14.0.0" + } + }, + "node_modules/@vitest/spy": { + "version": "3.2.4", + "resolved": "https://registry.npmjs.org/@vitest/spy/-/spy-3.2.4.tgz", + "integrity": "sha512-vAfasCOe6AIK70iP5UD11Ac4siNUNJ9i/9PZ3NKx07sG6sUxeag1LWdNrMWeKKYBLlzuK+Gn65Yd5nyL6ds+nw==", + "dev": true, + "license": "MIT", + "dependencies": { + "tinyspy": "^4.0.3" + }, + "funding": { + "url": "https://opencollective.com/vitest" + } + }, + "node_modules/@vitest/utils": { + "version": "3.2.4", + "resolved": "https://registry.npmjs.org/@vitest/utils/-/utils-3.2.4.tgz", + "integrity": "sha512-fB2V0JFrQSMsCo9HiSq3Ezpdv4iYaXRG1Sx8edX3MwxfyNn83mKiGzOcH+Fkxt4MHxr3y42fQi1oeAInqgX2QA==", + "dev": true, + "license": "MIT", + "dependencies": { + "@vitest/pretty-format": "3.2.4", + "loupe": "^3.1.4", + "tinyrainbow": "^2.0.0" + }, + "funding": { + "url": "https://opencollective.com/vitest" + } + }, + "node_modules/accepts": { + "version": "2.0.0", + "resolved": "https://registry.npmjs.org/accepts/-/accepts-2.0.0.tgz", + "integrity": "sha512-5cvg6CtKwfgdmVqY1WIiXKc3Q1bkRqGLi+2W/6ao+6Y7gu/RCwRuAhGEzh5B4KlszSuTLgZYuqFqo5bImjNKng==", + "dev": true, + "license": "MIT", + "dependencies": { + "mime-types": "^3.0.0", + "negotiator": "^1.0.0" }, "engines": { "node": ">= 0.6" @@ -3754,6 +3987,7 @@ "version": "8.15.0", "resolved": "https://registry.npmjs.org/acorn/-/acorn-8.15.0.tgz", "integrity": "sha512-NZyJarBfL7nWwIq+FDL6Zp/yHEhePMNnnJ0y3qfieCrmNvYct8uvtiV41UvlSe6apAfk0fY1FbWx+NwfmpvtTg==", + "dev": true, "license": "MIT", "bin": { "acorn": "bin/acorn" @@ -3793,6 +4027,7 @@ "version": "3.0.1", "resolved": "https://registry.npmjs.org/ajv-formats/-/ajv-formats-3.0.1.tgz", "integrity": "sha512-8iUql50EUR+uUcdRQ3HDqa6EVyo3docL8g5WJ3FNcWmu62IbkGUue/pEyLBW8VGKKucTPgqeks4fIU1DA4yowQ==", + "dev": true, "license": "MIT", "dependencies": { "ajv": "^8.0.0" @@ -3810,6 +4045,7 @@ "version": "8.18.0", "resolved": "https://registry.npmjs.org/ajv/-/ajv-8.18.0.tgz", "integrity": "sha512-PlXPeEWMXMZ7sPYOHqmDyCJzcfNrUr3fGNKtezX14ykXOEIvyK81d+qydx89KY5O71FKMPaQ2vBfBFI5NHR63A==", + "dev": true, "license": "MIT", "dependencies": { "fast-deep-equal": "^3.1.3", @@ -3826,6 +4062,7 @@ "version": "1.0.0", "resolved": "https://registry.npmjs.org/json-schema-traverse/-/json-schema-traverse-1.0.0.tgz", "integrity": "sha512-NM8/P9n3XjXhIZn1lLhkFaACTOURQXjWhV4BA/RnOv8xvgqtqpAX9IO4mRQxSx1Rlo4tqzeqb0sOlruaOy3dug==", + "dev": true, "license": "MIT" }, "node_modules/ansi-regex": { @@ -3834,6 +4071,7 @@ "integrity": "sha512-quJQXlTSUGL2LH9SUXo8VwsY4soanhgo6LNSm84E1LBcE8s3O0wpdiRzyR9z/ZZJMlMWv37qOOb9pdJlMUEKFQ==", "dev": true, "license": "MIT", + "peer": true, "engines": { "node": ">=8" } @@ -3895,9 +4133,9 @@ } }, "node_modules/ast-v8-to-istanbul": { - "version": "0.3.11", - "resolved": "https://registry.npmjs.org/ast-v8-to-istanbul/-/ast-v8-to-istanbul-0.3.11.tgz", - "integrity": "sha512-Qya9fkoofMjCBNVdWINMjB5KZvkYfaO9/anwkWnjxibpWUxo5iHl2sOdP7/uAqaRuUYuoo8rDwnbaaKVFxoUvw==", + "version": "1.0.3", + "resolved": "https://registry.npmjs.org/ast-v8-to-istanbul/-/ast-v8-to-istanbul-1.0.3.tgz", + "integrity": "sha512-jCMQ6ZylLPudp0CDfBmQBZUsrh1/8psbmu9ibeVWKuHWD0YrH9YABwlKu5kVEFoT0GCQQW9Z/SxfuEbbkGQCRg==", "dev": true, "license": "MIT", "dependencies": { @@ -3906,13 +4144,6 @@ "js-tokens": "^10.0.0" } }, - "node_modules/ast-v8-to-istanbul/node_modules/js-tokens": { - "version": "10.0.0", - "resolved": "https://registry.npmjs.org/js-tokens/-/js-tokens-10.0.0.tgz", - "integrity": "sha512-lM/UBzQmfJRo9ABXbPWemivdCW8V2G8FHaHdypQaIy523snUjog0W71ayWXTjiR+ixeMyVHN2XcpnTd/liPg/Q==", - "dev": true, - "license": "MIT" - }, "node_modules/async": { "version": "3.2.6", "resolved": "https://registry.npmjs.org/async/-/async-3.2.6.tgz", @@ -3934,6 +4165,7 @@ "version": "4.1.0", "resolved": "https://registry.npmjs.org/axobject-query/-/axobject-query-4.1.0.tgz", "integrity": "sha512-qIj0G9wZbMGNLjLmg1PT6v2mE9AH2zlnADJD/2tC6E00hgmhUOfEB6greHPAfLRSufHqROIUTkw6E+M3lH0PTQ==", + "dev": true, "license": "Apache-2.0", "engines": { "node": ">= 0.4" @@ -3943,6 +4175,7 @@ "version": "2.0.2", "resolved": "https://registry.npmjs.org/bail/-/bail-2.0.2.tgz", "integrity": "sha512-0xO6mYd7JB2YesxDKplafRpsiOzPt9V02ddPCLbY1xYGPOX24NTyN50qnUxgCPcSoYMhKpAuBTjQoRZCAkUDRw==", + "dev": true, "license": "MIT", "funding": { "type": "github", @@ -4044,6 +4277,7 @@ "version": "2.2.2", "resolved": "https://registry.npmjs.org/body-parser/-/body-parser-2.2.2.tgz", "integrity": "sha512-oP5VkATKlNwcgvxi0vM0p/D3n2C3EReYVX+DNYs5TjZFn/oQt2j+4sVJtSMr18pdRr8wjTcBl6LoV+FUwzPmNA==", + "dev": true, "license": "MIT", "dependencies": { "bytes": "^3.1.2", @@ -4068,6 +4302,7 @@ "version": "0.7.2", "resolved": "https://registry.npmjs.org/iconv-lite/-/iconv-lite-0.7.2.tgz", "integrity": "sha512-im9DjEDQ55s9fL4EYzOAv0yMqmMBSZp6G0VvFyTMPKWxiSBHUj9NW/qqLmXUwXrrM7AvqSlTCfvqRb0cM8yYqw==", + "dev": true, "license": "MIT", "dependencies": { "safer-buffer": ">= 2.1.2 < 3.0.0" @@ -4125,25 +4360,17 @@ "version": "3.1.2", "resolved": "https://registry.npmjs.org/bytes/-/bytes-3.1.2.tgz", "integrity": "sha512-/Nf7TyzTx6S3yRJObOAV7956r8cr2+Oj8AC5dt8wSP3BQAoeX58NoHyCU8P8zGkNXStjTSi6fzO6F0pBdcYbEg==", - "license": "MIT", - "engines": { - "node": ">= 0.8" - } - }, - "node_modules/cac": { - "version": "6.7.14", - "resolved": "https://registry.npmjs.org/cac/-/cac-6.7.14.tgz", - "integrity": "sha512-b6Ilus+c3RrdDk+JhLKUAQfzzgLEPy6wcXqS7f/xe1EETvsDP6GORG7SFuOs6cID5YkqchW/LXZbX5bc8j7ZcQ==", "dev": true, "license": "MIT", "engines": { - "node": ">=8" + "node": ">= 0.8" } }, "node_modules/call-bind-apply-helpers": { "version": "1.0.2", "resolved": "https://registry.npmjs.org/call-bind-apply-helpers/-/call-bind-apply-helpers-1.0.2.tgz", "integrity": "sha512-Sp1ablJ0ivDkSzjcaJdxEunN5/XvksFJ2sMBFfq6x0ryhQV/2b/KwFe21cMpmHtPOSij8K99/wSfoEuTObmuMQ==", + "dev": true, "license": "MIT", "dependencies": { "es-errors": "^1.3.0", @@ -4157,6 +4384,7 @@ "version": "1.0.4", "resolved": "https://registry.npmjs.org/call-bound/-/call-bound-1.0.4.tgz", "integrity": "sha512-+ys997U96po4Kx/ABpBCqhA9EuxJaQWDQg7295H4hBphv3IZg0boBKuwYpt4YXp6MZ5AmZQnU/tyMTlRpaSejg==", + "dev": true, "license": "MIT", "dependencies": { "call-bind-apply-helpers": "^1.0.2", @@ -4183,6 +4411,7 @@ "version": "2.0.1", "resolved": "https://registry.npmjs.org/ccount/-/ccount-2.0.1.tgz", "integrity": "sha512-eyrF0jiFpY+3drT6383f1qhkbGsLSifNAjA61IUjZjmLCWjItY6LB9ft9YhoDgwfmclB2zhu51Lc7+95b8NRAg==", + "dev": true, "license": "MIT", "funding": { "type": "github", @@ -4227,6 +4456,7 @@ "version": "2.0.2", "resolved": "https://registry.npmjs.org/character-entities/-/character-entities-2.0.2.tgz", "integrity": "sha512-shx7oQ0Awen/BRIdkjkvz54PnEEI/EjwXDSIZp86/KKdbafHh1Df/RYGBhn4hbe2+uKC9FnT5UCEdyPz3ai9hQ==", + "dev": true, "license": "MIT", "funding": { "type": "github", @@ -4237,6 +4467,7 @@ "version": "2.1.0", "resolved": "https://registry.npmjs.org/character-entities-html4/-/character-entities-html4-2.1.0.tgz", "integrity": "sha512-1v7fgQRj6hnSwFpq1Eu0ynr/CDEw0rXo2B61qXrLNdHZmPKgb7fqS1a2JwF0rISo9q77jDI8VMEHoApn8qDoZA==", + "dev": true, "license": "MIT", "funding": { "type": "github", @@ -4247,6 +4478,7 @@ "version": "3.0.0", "resolved": "https://registry.npmjs.org/character-entities-legacy/-/character-entities-legacy-3.0.0.tgz", "integrity": "sha512-RpPp0asT/6ufRm//AJVwpViZbGM/MkjQFxJccQRHmISF/22NBtsHqAWmL+/pmkPWoIUJdWyeVleTl1wydHATVQ==", + "dev": true, "license": "MIT", "funding": { "type": "github", @@ -4317,6 +4549,7 @@ "version": "2.1.1", "resolved": "https://registry.npmjs.org/clsx/-/clsx-2.1.1.tgz", "integrity": "sha512-eYm0QWBtUrBWZWG0d386OGAw16Z995PiOVo2B7bjWSbHedGl5e0ZWaq65kOGgUSNesEIDkB9ISbTg/JK9dhCZA==", + "dev": true, "license": "MIT", "engines": { "node": ">=6" @@ -4346,6 +4579,7 @@ "version": "2.0.3", "resolved": "https://registry.npmjs.org/comma-separated-tokens/-/comma-separated-tokens-2.0.3.tgz", "integrity": "sha512-Fu4hJdvzeylCfQPp9SGWidpzrMs7tTrlu6Vb8XGaRGck8QSNZJJp538Wrb60Lax4fPwR64ViY468OIUTbRlGZg==", + "dev": true, "license": "MIT", "funding": { "type": "github", @@ -4356,6 +4590,7 @@ "version": "8.3.0", "resolved": "https://registry.npmjs.org/commander/-/commander-8.3.0.tgz", "integrity": "sha512-OkTL9umf+He2DZkUq8f8J9of7yL6RJKI24dVITBmNfZBmri9zYZQrKkuXiKhyfPSu8tUhnVBB1iKXevvnlR4Ww==", + "dev": true, "license": "MIT", "engines": { "node": ">= 12" @@ -4372,6 +4607,7 @@ "version": "1.0.1", "resolved": "https://registry.npmjs.org/content-disposition/-/content-disposition-1.0.1.tgz", "integrity": "sha512-oIXISMynqSqm241k6kcQ5UwttDILMK4BiurCfGEREw6+X9jkkpEe5T9FZaApyLGGOnFuyMWZpdolTXMtvEJ08Q==", + "dev": true, "license": "MIT", "engines": { "node": ">=18" @@ -4385,25 +4621,38 @@ "version": "1.0.5", "resolved": "https://registry.npmjs.org/content-type/-/content-type-1.0.5.tgz", "integrity": "sha512-nTjqfcBFEipKdXCv4YDQWCfmcLZKm81ldF0pAopTvyrFGVbcR6P/VAAd5G7N+0tTr8QqiU0tFadD6FK4NtJwOA==", + "dev": true, "license": "MIT", "engines": { "node": ">= 0.6" } }, + "node_modules/convert-source-map": { + "version": "2.0.0", + "resolved": "https://registry.npmjs.org/convert-source-map/-/convert-source-map-2.0.0.tgz", + "integrity": "sha512-Kvp459HrV2FEJ1CAsi1Ku+MY3kasH19TFykTz2xWmMeq6bk2NU3XXvfJ+Q61m0xktWwt+1HSYf3JZsTms3aRJg==", + "dev": true, + "license": "MIT" + }, "node_modules/cookie": { - "version": "0.6.0", - "resolved": "https://registry.npmjs.org/cookie/-/cookie-0.6.0.tgz", - "integrity": "sha512-U71cyTamuh1CRNCfpGY6to28lxvNwPG4Guz/EVjgf3Jmzv0vlDp1atT9eS5dDjMYHucpHbWns6Lwf3BKz6svdw==", + "version": "1.1.1", + "resolved": "https://registry.npmjs.org/cookie/-/cookie-1.1.1.tgz", + "integrity": "sha512-ei8Aos7ja0weRpFzJnEA9UHJ/7XQmqglbRwnf2ATjcB9Wq874VKH9kfjjirM6UhU2/E5fFYadylyhFldcqSidQ==", "dev": true, "license": "MIT", "engines": { - "node": ">= 0.6" + "node": ">=18" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/express" } }, "node_modules/cookie-signature": { "version": "1.2.2", "resolved": "https://registry.npmjs.org/cookie-signature/-/cookie-signature-1.2.2.tgz", "integrity": "sha512-D76uU73ulSXrD1UXF4KE2TMxVVwhsnCgfAyTg9k8P6KGZjlXKrOLe4dJQKI3Bxi5wjesZoFXJWElNWBjPZMbhg==", + "dev": true, "license": "MIT", "engines": { "node": ">=6.6.0" @@ -4413,6 +4662,7 @@ "version": "2.8.5", "resolved": "https://registry.npmjs.org/cors/-/cors-2.8.5.tgz", "integrity": "sha512-KIHbLJqu73RGr/hnbrO9uBeixNGuvSQjul/jdFvS/KFSIH1hWVd1ng7zOHx+YrEfInLG7q4n6GHQ9cDtxv/P6g==", + "dev": true, "license": "MIT", "dependencies": { "object-assign": "^4", @@ -4436,6 +4686,7 @@ "version": "1.0.3", "resolved": "https://registry.npmjs.org/cose-base/-/cose-base-1.0.3.tgz", "integrity": "sha512-s9whTXInMSgAp/NVXVNuVxVKzGH2qck3aQlVHxDCdAEPgtMKwc4Wq6/QKhgdEdgbLSi9rBTAcPoRa6JpiG4ksg==", + "dev": true, "license": "MIT", "dependencies": { "layout-base": "^1.0.0" @@ -4445,6 +4696,7 @@ "version": "7.0.6", "resolved": "https://registry.npmjs.org/cross-spawn/-/cross-spawn-7.0.6.tgz", "integrity": "sha512-uV2QOWP2nWzsy2aMp8aRibhi9dlzF5Hgh5SHaB9OiTGEyDTiJJyx0uy51QXdyWbtAHNua4XJzUKca3OzKUd3vA==", + "dev": true, "license": "MIT", "dependencies": { "path-key": "^3.1.0", @@ -4476,17 +4728,18 @@ } }, "node_modules/csstype": { - "version": "3.1.3", - "resolved": "https://registry.npmjs.org/csstype/-/csstype-3.1.3.tgz", - "integrity": "sha512-M1uQkMl8rQK/szD0LNhtqxIPLpimGm8sOBwU7lLnCpSbTyY3yeU1Vc7l4KT5zT4s/yOxHH5O7tIuuLOCnLADRw==", + "version": "3.2.3", + "resolved": "https://registry.npmjs.org/csstype/-/csstype-3.2.3.tgz", + "integrity": "sha512-z1HGKcYy2xA8AGQfwrn0PAy+PB7X/GSj3UVJW9qKyn43xWa+gl5nXmU4qqLMRzWVLFC8KusUX8T/0kCiOYpAIQ==", "dev": true, "license": "MIT", "peer": true }, "node_modules/cytoscape": { - "version": "3.33.4", - "resolved": "https://registry.npmjs.org/cytoscape/-/cytoscape-3.33.4.tgz", - "integrity": "sha512-HIN5Pmd9MrX9BkV7tDwnOcEJCSFvCpc8X97h3f508J6I5FsqAY65wKOCvgH2CuP42CaahWaz4tuh32SOOIH7ww==", + "version": "3.34.0", + "resolved": "https://registry.npmjs.org/cytoscape/-/cytoscape-3.34.0.tgz", + "integrity": "sha512-62rNSrioXw93uliKFBwjukeQyeWwH2PqDrTac31r2P6464u3AUvTk0xS4LVvT251g7IgkFunrI48ZEZGjywSOg==", + "dev": true, "license": "MIT", "engines": { "node": ">=0.10" @@ -4496,6 +4749,7 @@ "version": "4.1.0", "resolved": "https://registry.npmjs.org/cytoscape-cose-bilkent/-/cytoscape-cose-bilkent-4.1.0.tgz", "integrity": "sha512-wgQlVIUJF13Quxiv5e1gstZ08rnZj2XaLHGoFMYXz7SkNfCDOOteKBE6SYRfA9WxxI/iBc3ajfDoc6hb/MRAHQ==", + "dev": true, "license": "MIT", "dependencies": { "cose-base": "^1.0.0" @@ -4508,6 +4762,7 @@ "version": "2.2.0", "resolved": "https://registry.npmjs.org/cytoscape-fcose/-/cytoscape-fcose-2.2.0.tgz", "integrity": "sha512-ki1/VuRIHFCzxWNrsshHYPs6L7TvLu3DL+TyIGEsRcvVERmxokbf5Gdk7mFxZnTdiGtnA4cfSmjZJMviqSuZrQ==", + "dev": true, "license": "MIT", "dependencies": { "cose-base": "^2.2.0" @@ -4520,6 +4775,7 @@ "version": "2.2.0", "resolved": "https://registry.npmjs.org/cose-base/-/cose-base-2.2.0.tgz", "integrity": "sha512-AzlgcsCbUMymkADOJtQm3wO9S3ltPfYOFD5033keQn9NJzIbtnZj+UdBJe7DYml/8TdbtHJW3j58SOnKhWY/5g==", + "dev": true, "license": "MIT", "dependencies": { "layout-base": "^2.0.0" @@ -4529,12 +4785,14 @@ "version": "2.0.1", "resolved": "https://registry.npmjs.org/layout-base/-/layout-base-2.0.1.tgz", "integrity": "sha512-dp3s92+uNI1hWIpPGH3jK2kxE2lMjdXdr+DH8ynZHpd6PUlH6x6cbuXnoMmiNumznqaNO31xu9e79F0uuZ0JFg==", + "dev": true, "license": "MIT" }, "node_modules/d3": { "version": "7.9.0", "resolved": "https://registry.npmjs.org/d3/-/d3-7.9.0.tgz", "integrity": "sha512-e1U46jVP+w7Iut8Jt8ri1YsPOvFpg46k+K8TpCb0P+zjCkjkPnV7WzfDJzMHy1LnA+wj5pLT1wjO901gLXeEhA==", + "dev": true, "license": "ISC", "dependencies": { "d3-array": "3", @@ -4576,6 +4834,7 @@ "version": "3.2.4", "resolved": "https://registry.npmjs.org/d3-array/-/d3-array-3.2.4.tgz", "integrity": "sha512-tdQAmyA18i4J7wprpYq8ClcxZy3SC31QMeByyCFyRt7BVHdREQZ5lpzoe5mFEYZUWe+oq8HBvk9JjpibyEV4Jg==", + "dev": true, "license": "ISC", "dependencies": { "internmap": "1 - 2" @@ -4588,6 +4847,7 @@ "version": "3.0.0", "resolved": "https://registry.npmjs.org/d3-axis/-/d3-axis-3.0.0.tgz", "integrity": "sha512-IH5tgjV4jE/GhHkRV0HiVYPDtvfjHQlQfJHs0usq7M30XcSBvOotpmH1IgkcXsO/5gEQZD43B//fc7SRT5S+xw==", + "dev": true, "license": "ISC", "engines": { "node": ">=12" @@ -4597,6 +4857,7 @@ "version": "3.0.0", "resolved": "https://registry.npmjs.org/d3-brush/-/d3-brush-3.0.0.tgz", "integrity": "sha512-ALnjWlVYkXsVIGlOsuWH1+3udkYFI48Ljihfnh8FZPF2QS9o+PzGLBslO0PjzVoHLZ2KCVgAM8NVkXPJB2aNnQ==", + "dev": true, "license": "ISC", "dependencies": { "d3-dispatch": "1 - 3", @@ -4613,6 +4874,7 @@ "version": "3.0.1", "resolved": "https://registry.npmjs.org/d3-chord/-/d3-chord-3.0.1.tgz", "integrity": "sha512-VE5S6TNa+j8msksl7HwjxMHDM2yNK3XCkusIlpX5kwauBfXuyLAtNg9jCp/iHH61tgI4sb6R/EIMWCqEIdjT/g==", + "dev": true, "license": "ISC", "dependencies": { "d3-path": "1 - 3" @@ -4625,6 +4887,7 @@ "version": "3.1.0", "resolved": "https://registry.npmjs.org/d3-color/-/d3-color-3.1.0.tgz", "integrity": "sha512-zg/chbXyeBtMQ1LbD/WSoW2DpC3I0mpmPdW+ynRTj/x2DAWYrIY7qeZIHidozwV24m4iavr15lNwIwLxRmOxhA==", + "dev": true, "license": "ISC", "engines": { "node": ">=12" @@ -4634,6 +4897,7 @@ "version": "4.0.2", "resolved": "https://registry.npmjs.org/d3-contour/-/d3-contour-4.0.2.tgz", "integrity": "sha512-4EzFTRIikzs47RGmdxbeUvLWtGedDUNkTcmzoeyg4sP/dvCexO47AaQL7VKy/gul85TOxw+IBgA8US2xwbToNA==", + "dev": true, "license": "ISC", "dependencies": { "d3-array": "^3.2.0" @@ -4646,6 +4910,7 @@ "version": "6.0.4", "resolved": "https://registry.npmjs.org/d3-delaunay/-/d3-delaunay-6.0.4.tgz", "integrity": "sha512-mdjtIZ1XLAM8bm/hx3WwjfHt6Sggek7qH043O8KEjDXN40xi3vx/6pYSVTwLjEgiXQTbvaouWKynLBiUZ6SK6A==", + "dev": true, "license": "ISC", "dependencies": { "delaunator": "5" @@ -4658,6 +4923,7 @@ "version": "3.0.1", "resolved": "https://registry.npmjs.org/d3-dispatch/-/d3-dispatch-3.0.1.tgz", "integrity": "sha512-rzUyPU/S7rwUflMyLc1ETDeBj0NRuHKKAcvukozwhshr6g6c5d8zh4c2gQjY2bZ0dXeGLWc1PF174P2tVvKhfg==", + "dev": true, "license": "ISC", "engines": { "node": ">=12" @@ -4667,6 +4933,7 @@ "version": "3.0.0", "resolved": "https://registry.npmjs.org/d3-drag/-/d3-drag-3.0.0.tgz", "integrity": "sha512-pWbUJLdETVA8lQNJecMxoXfH6x+mO2UQo8rSmZ+QqxcbyA3hfeprFgIT//HW2nlHChWeIIMwS2Fq+gEARkhTkg==", + "dev": true, "license": "ISC", "dependencies": { "d3-dispatch": "1 - 3", @@ -4680,6 +4947,7 @@ "version": "3.0.1", "resolved": "https://registry.npmjs.org/d3-dsv/-/d3-dsv-3.0.1.tgz", "integrity": "sha512-UG6OvdI5afDIFP9w4G0mNq50dSOsXHJaRE8arAS5o9ApWnIElp8GZw1Dun8vP8OyHOZ/QJUKUJwxiiCCnUwm+Q==", + "dev": true, "license": "ISC", "dependencies": { "commander": "7", @@ -4705,6 +4973,7 @@ "version": "7.2.0", "resolved": "https://registry.npmjs.org/commander/-/commander-7.2.0.tgz", "integrity": "sha512-QrWXB+ZQSVPmIWIhtEO9H+gwHaMGYiF5ChvoJ+K9ZGHG/sVsa6yiesAD1GC/x46sET00Xlwo1u49RVVVzvcSkw==", + "dev": true, "license": "MIT", "engines": { "node": ">= 10" @@ -4714,6 +4983,7 @@ "version": "3.0.1", "resolved": "https://registry.npmjs.org/d3-ease/-/d3-ease-3.0.1.tgz", "integrity": "sha512-wR/XK3D3XcLIZwpbvQwQ5fK+8Ykds1ip7A2Txe0yxncXSdq1L9skcG7blcedkOX+ZcgxGAmLX1FrRGbADwzi0w==", + "dev": true, "license": "BSD-3-Clause", "engines": { "node": ">=12" @@ -4723,6 +4993,7 @@ "version": "3.0.1", "resolved": "https://registry.npmjs.org/d3-fetch/-/d3-fetch-3.0.1.tgz", "integrity": "sha512-kpkQIM20n3oLVBKGg6oHrUchHM3xODkTzjMoj7aWQFq5QEM+R6E4WkzT5+tojDY7yjez8KgCBRoj4aEr99Fdqw==", + "dev": true, "license": "ISC", "dependencies": { "d3-dsv": "1 - 3" @@ -4735,6 +5006,7 @@ "version": "3.0.0", "resolved": "https://registry.npmjs.org/d3-force/-/d3-force-3.0.0.tgz", "integrity": "sha512-zxV/SsA+U4yte8051P4ECydjD/S+qeYtnaIyAs9tgHCqfguma/aAQDjo85A9Z6EKhBirHRJHXIgJUlffT4wdLg==", + "dev": true, "license": "ISC", "dependencies": { "d3-dispatch": "1 - 3", @@ -4749,6 +5021,7 @@ "version": "3.1.2", "resolved": "https://registry.npmjs.org/d3-format/-/d3-format-3.1.2.tgz", "integrity": "sha512-AJDdYOdnyRDV5b6ArilzCPPwc1ejkHcoyFarqlPqT7zRYjhavcT3uSrqcMvsgh2CgoPbK3RCwyHaVyxYcP2Arg==", + "dev": true, "license": "ISC", "engines": { "node": ">=12" @@ -4758,6 +5031,7 @@ "version": "3.1.1", "resolved": "https://registry.npmjs.org/d3-geo/-/d3-geo-3.1.1.tgz", "integrity": "sha512-637ln3gXKXOwhalDzinUgY83KzNWZRKbYubaG+fGVuc/dxO64RRljtCTnf5ecMyE1RIdtqpkVcq0IbtU2S8j2Q==", + "dev": true, "license": "ISC", "dependencies": { "d3-array": "2.5.0 - 3" @@ -4770,6 +5044,7 @@ "version": "3.1.2", "resolved": "https://registry.npmjs.org/d3-hierarchy/-/d3-hierarchy-3.1.2.tgz", "integrity": "sha512-FX/9frcub54beBdugHjDCdikxThEqjnR93Qt7PvQTOHxyiNCAlvMrHhclk3cD5VeAaq9fxmfRp+CnWw9rEMBuA==", + "dev": true, "license": "ISC", "engines": { "node": ">=12" @@ -4779,6 +5054,7 @@ "version": "3.0.1", "resolved": "https://registry.npmjs.org/d3-interpolate/-/d3-interpolate-3.0.1.tgz", "integrity": "sha512-3bYs1rOD33uo8aqJfKP3JWPAibgw8Zm2+L9vBKEHJ2Rg+viTR7o5Mmv5mZcieN+FRYaAOWX5SJATX6k1PWz72g==", + "dev": true, "license": "ISC", "dependencies": { "d3-color": "1 - 3" @@ -4791,6 +5067,7 @@ "version": "3.1.0", "resolved": "https://registry.npmjs.org/d3-path/-/d3-path-3.1.0.tgz", "integrity": "sha512-p3KP5HCf/bvjBSSKuXid6Zqijx7wIfNW+J/maPs+iwR35at5JCbLUT0LzF1cnjbCHWhqzQTIN2Jpe8pRebIEFQ==", + "dev": true, "license": "ISC", "engines": { "node": ">=12" @@ -4800,6 +5077,7 @@ "version": "3.0.1", "resolved": "https://registry.npmjs.org/d3-polygon/-/d3-polygon-3.0.1.tgz", "integrity": "sha512-3vbA7vXYwfe1SYhED++fPUQlWSYTTGmFmQiany/gdbiWgU/iEyQzyymwL9SkJjFFuCS4902BSzewVGsHHmHtXg==", + "dev": true, "license": "ISC", "engines": { "node": ">=12" @@ -4809,6 +5087,7 @@ "version": "3.0.1", "resolved": "https://registry.npmjs.org/d3-quadtree/-/d3-quadtree-3.0.1.tgz", "integrity": "sha512-04xDrxQTDTCFwP5H6hRhsRcb9xxv2RzkcsygFzmkSIOJy3PeRJP7sNk3VRIbKXcog561P9oU0/rVH6vDROAgUw==", + "dev": true, "license": "ISC", "engines": { "node": ">=12" @@ -4818,6 +5097,7 @@ "version": "3.0.1", "resolved": "https://registry.npmjs.org/d3-random/-/d3-random-3.0.1.tgz", "integrity": "sha512-FXMe9GfxTxqd5D6jFsQ+DJ8BJS4E/fT5mqqdjovykEB2oFbTMDVdg1MGFxfQW+FBOGoB++k8swBrgwSHT1cUXQ==", + "dev": true, "license": "ISC", "engines": { "node": ">=12" @@ -4827,6 +5107,7 @@ "version": "0.12.3", "resolved": "https://registry.npmjs.org/d3-sankey/-/d3-sankey-0.12.3.tgz", "integrity": "sha512-nQhsBRmM19Ax5xEIPLMY9ZmJ/cDvd1BG3UVvt5h3WRxKg5zGRbvnteTyWAbzeSvlh3tW7ZEmq4VwR5mB3tutmQ==", + "dev": true, "license": "BSD-3-Clause", "dependencies": { "d3-array": "1 - 2", @@ -4837,6 +5118,7 @@ "version": "2.12.1", "resolved": "https://registry.npmjs.org/d3-array/-/d3-array-2.12.1.tgz", "integrity": "sha512-B0ErZK/66mHtEsR1TkPEEkwdy+WDesimkM5gpZr5Dsg54BiTA5RXtYW5qTLIAcekaS9xfZrzBLF/OAkB3Qn1YQ==", + "dev": true, "license": "BSD-3-Clause", "dependencies": { "internmap": "^1.0.0" @@ -4846,12 +5128,14 @@ "version": "1.0.9", "resolved": "https://registry.npmjs.org/d3-path/-/d3-path-1.0.9.tgz", "integrity": "sha512-VLaYcn81dtHVTjEHd8B+pbe9yHWpXKZUC87PzoFmsFrJqgFwDe/qxfp5MlfsfM1V5E/iVt0MmEbWQ7FVIXh/bg==", + "dev": true, "license": "BSD-3-Clause" }, "node_modules/d3-sankey/node_modules/d3-shape": { "version": "1.3.7", "resolved": "https://registry.npmjs.org/d3-shape/-/d3-shape-1.3.7.tgz", "integrity": "sha512-EUkvKjqPFUAZyOlhY5gzCxCeI0Aep04LwIRpsZ/mLFelJiUfnK56jo5JMDSE7yyP2kLSb6LtF+S5chMk7uqPqw==", + "dev": true, "license": "BSD-3-Clause", "dependencies": { "d3-path": "1" @@ -4861,12 +5145,14 @@ "version": "1.0.1", "resolved": "https://registry.npmjs.org/internmap/-/internmap-1.0.1.tgz", "integrity": "sha512-lDB5YccMydFBtasVtxnZ3MRBHuaoE8GKsppq+EchKL2U4nK/DmEpPHNH8MZe5HkMtpSiTSOZwfN0tzYjO/lJEw==", + "dev": true, "license": "ISC" }, "node_modules/d3-scale": { "version": "4.0.2", "resolved": "https://registry.npmjs.org/d3-scale/-/d3-scale-4.0.2.tgz", "integrity": "sha512-GZW464g1SH7ag3Y7hXjf8RoUuAFIqklOAq3MRl4OaWabTFJY9PN/E1YklhXLh+OQ3fM9yS2nOkCoS+WLZ6kvxQ==", + "dev": true, "license": "ISC", "dependencies": { "d3-array": "2.10.0 - 3", @@ -4883,6 +5169,7 @@ "version": "3.1.0", "resolved": "https://registry.npmjs.org/d3-scale-chromatic/-/d3-scale-chromatic-3.1.0.tgz", "integrity": "sha512-A3s5PWiZ9YCXFye1o246KoscMWqf8BsD9eRiJ3He7C9OBaxKhAd5TFCdEx/7VbKtxxTsu//1mMJFrEt572cEyQ==", + "dev": true, "license": "ISC", "dependencies": { "d3-color": "1 - 3", @@ -4896,6 +5183,7 @@ "version": "3.0.0", "resolved": "https://registry.npmjs.org/d3-selection/-/d3-selection-3.0.0.tgz", "integrity": "sha512-fmTRWbNMmsmWq6xJV8D19U/gw/bwrHfNXxrIN+HfZgnzqTHp9jOmKMhsTUjXOJnZOdZY9Q28y4yebKzqDKlxlQ==", + "dev": true, "license": "ISC", "engines": { "node": ">=12" @@ -4905,6 +5193,7 @@ "version": "3.2.0", "resolved": "https://registry.npmjs.org/d3-shape/-/d3-shape-3.2.0.tgz", "integrity": "sha512-SaLBuwGm3MOViRq2ABk3eLoxwZELpH6zhl3FbAoJ7Vm1gofKx6El1Ib5z23NUEhF9AsGl7y+dzLe5Cw2AArGTA==", + "dev": true, "license": "ISC", "dependencies": { "d3-path": "^3.1.0" @@ -4917,6 +5206,7 @@ "version": "3.1.0", "resolved": "https://registry.npmjs.org/d3-time/-/d3-time-3.1.0.tgz", "integrity": "sha512-VqKjzBLejbSMT4IgbmVgDjpkYrNWUYJnbCGo874u7MMKIWsILRX+OpX/gTk8MqjpT1A/c6HY2dCA77ZN0lkQ2Q==", + "dev": true, "license": "ISC", "dependencies": { "d3-array": "2 - 3" @@ -4929,6 +5219,7 @@ "version": "4.1.0", "resolved": "https://registry.npmjs.org/d3-time-format/-/d3-time-format-4.1.0.tgz", "integrity": "sha512-dJxPBlzC7NugB2PDLwo9Q8JiTR3M3e4/XANkreKSUxF8vvXKqm1Yfq4Q5dl8budlunRVlUUaDUgFt7eA8D6NLg==", + "dev": true, "license": "ISC", "dependencies": { "d3-time": "1 - 3" @@ -4941,6 +5232,7 @@ "version": "3.0.1", "resolved": "https://registry.npmjs.org/d3-timer/-/d3-timer-3.0.1.tgz", "integrity": "sha512-ndfJ/JxxMd3nw31uyKoY2naivF+r29V+Lc0svZxe1JvvIRmi8hUsrMvdOwgS1o6uBHmiz91geQ0ylPP0aj1VUA==", + "dev": true, "license": "ISC", "engines": { "node": ">=12" @@ -4950,6 +5242,7 @@ "version": "3.0.1", "resolved": "https://registry.npmjs.org/d3-transition/-/d3-transition-3.0.1.tgz", "integrity": "sha512-ApKvfjsSR6tg06xrL434C0WydLr7JewBB3V+/39RMHsaXTOG0zmt/OAXeng5M5LBm0ojmxJrpomQVZ1aPvBL4w==", + "dev": true, "license": "ISC", "dependencies": { "d3-color": "1 - 3", @@ -4969,6 +5262,7 @@ "version": "3.0.0", "resolved": "https://registry.npmjs.org/d3-zoom/-/d3-zoom-3.0.0.tgz", "integrity": "sha512-b8AmV3kfQaqWAuacbPuNbL6vahnOJflOhexLzMMNLga62+/nh0JzvJ0aO/5a5MVgUFGS7Hu1P9P03o3fJkDCyw==", + "dev": true, "license": "ISC", "dependencies": { "d3-dispatch": "1 - 3", @@ -4985,6 +5279,7 @@ "version": "7.0.14", "resolved": "https://registry.npmjs.org/dagre-d3-es/-/dagre-d3-es-7.0.14.tgz", "integrity": "sha512-P4rFMVq9ESWqmOgK+dlXvOtLwYg0i7u0HBGJER0LZDJT2VHIPAMZ/riPxqJceWMStH5+E61QxFra9kIS3AqdMg==", + "dev": true, "license": "MIT", "dependencies": { "d3": "^7.9.0", @@ -4992,15 +5287,17 @@ } }, "node_modules/dayjs": { - "version": "1.11.20", - "resolved": "https://registry.npmjs.org/dayjs/-/dayjs-1.11.20.tgz", - "integrity": "sha512-YbwwqR/uYpeoP4pu043q+LTDLFBLApUP6VxRihdfNTqu4ubqMlGDLd6ErXhEgsyvY0K6nCs7nggYumAN+9uEuQ==", + "version": "1.11.21", + "resolved": "https://registry.npmjs.org/dayjs/-/dayjs-1.11.21.tgz", + "integrity": "sha512-98IT+HOahAisibz/yjKbzuOBwYcjJ7BCLPzARyHiyEBmRz4fatF+KPJszEHXsGYjUG234aH/cOjW1wwTbKUZlA==", + "dev": true, "license": "MIT" }, "node_modules/debug": { "version": "4.4.3", "resolved": "https://registry.npmjs.org/debug/-/debug-4.4.3.tgz", "integrity": "sha512-RGwwWnwQvkVfavKVt22FGLw+xYSdzARwm0ru6DhTVA3umU5hZc28V3kO4stgYryrTlLpuvgI9GiijltAjNbcqA==", + "dev": true, "license": "MIT", "dependencies": { "ms": "^2.1.3" @@ -5018,6 +5315,7 @@ "version": "1.2.0", "resolved": "https://registry.npmjs.org/decode-named-character-reference/-/decode-named-character-reference-1.2.0.tgz", "integrity": "sha512-c6fcElNV6ShtZXmsgNgFFV5tVX2PaV4g+MOAkb8eXHvn6sryJBrZa9r0zV6+dtTyoCKxtDy5tyQ5ZwQuidtd+Q==", + "dev": true, "license": "MIT", "dependencies": { "character-entities": "^2.0.0" @@ -5123,6 +5421,7 @@ "version": "5.1.0", "resolved": "https://registry.npmjs.org/delaunator/-/delaunator-5.1.0.tgz", "integrity": "sha512-AGrQ4QSgssa1NGmWmLPqN5NY2KajF5MqxetNEO+o0n3ZwZZeTmt7bBnvzHWrmkZFxGgr4HdyFgelzgi06otLuQ==", + "dev": true, "license": "ISC", "dependencies": { "robust-predicates": "^3.0.2" @@ -5132,6 +5431,7 @@ "version": "2.0.0", "resolved": "https://registry.npmjs.org/depd/-/depd-2.0.0.tgz", "integrity": "sha512-g7nH6P6dyDioJogAAGprGpCtVImJhpPk/roCzdb3fIh61/s/nPsfR6onyMwkCAR/OlC3yBC0lESvUoQEAssIrw==", + "dev": true, "license": "MIT", "engines": { "node": ">= 0.8" @@ -5141,6 +5441,7 @@ "version": "2.0.3", "resolved": "https://registry.npmjs.org/dequal/-/dequal-2.0.3.tgz", "integrity": "sha512-0je+qPKHEMohvfRTCEo3CrPG6cAzAYgmzKyxRiYSSDkS6eGJdyVJm7WaYA5ECaAD9wLB2T4EEeymA5aFVcYXCA==", + "dev": true, "license": "MIT", "engines": { "node": ">=6" @@ -5160,12 +5461,14 @@ "version": "5.8.1", "resolved": "https://registry.npmjs.org/devalue/-/devalue-5.8.1.tgz", "integrity": "sha512-4CXDYRBGqN+57wVJkuXBYmpAVUSg3L6JAQa/DFqm238G73E1wuyc/JhGQJzN7vUf/CMphYau2zXbfWzDR5aTEw==", + "dev": true, "license": "MIT" }, "node_modules/devlop": { "version": "1.1.0", "resolved": "https://registry.npmjs.org/devlop/-/devlop-1.1.0.tgz", "integrity": "sha512-RWmIqhcFf1lRYBvNmr7qTNuyCt/7/ns2jbpp1+PalgE/rDQcBT0fioSMUpJ93irlUhC5hrg4cYqe6U+0ImW0rA==", + "dev": true, "license": "MIT", "dependencies": { "dequal": "^2.0.0" @@ -5187,12 +5490,14 @@ "resolved": "https://registry.npmjs.org/dom-accessibility-api/-/dom-accessibility-api-0.5.16.tgz", "integrity": "sha512-X7BJ2yElsnOJ30pZF4uIIDfBEVgF4XEBxL9Bxhy6dnrm5hkzqmsWHGTiHqRiITNhMyFLyAiWndIJP7Z1NTteDg==", "dev": true, - "license": "MIT" + "license": "MIT", + "peer": true }, "node_modules/dompurify": { - "version": "3.4.5", - "resolved": "https://registry.npmjs.org/dompurify/-/dompurify-3.4.5.tgz", - "integrity": "sha512-OrwIBKsdNSVEeubdJ1HBv/wNENRM9ytAVCv7YXt//A3vPdVMNuACRqK9mXCGCBW2ln7BT/A4X0jXHo2Gu89miA==", + "version": "3.4.8", + "resolved": "https://registry.npmjs.org/dompurify/-/dompurify-3.4.8.tgz", + "integrity": "sha512-yb1cEmaOum7wFvOCSQxyfgVlv5D47Rc30iZWoMpbDIWTnJ6grDDQyu2KFJzB2k7u0pMuJcQ1zphH//fFnw2tjQ==", + "dev": true, "license": "(MPL-2.0 OR Apache-2.0)", "optionalDependencies": { "@types/trusted-types": "^2.0.7" @@ -5202,6 +5507,7 @@ "version": "1.0.1", "resolved": "https://registry.npmjs.org/dunder-proto/-/dunder-proto-1.0.1.tgz", "integrity": "sha512-KIN/nDJBQRcXw0MLVhZE9iQHmG68qAVIBg9CqmUYjmQIhgij9U5MFvrqkUL5FbtyyzZuOeOt0zdeRe4UY7ct+A==", + "dev": true, "license": "MIT", "dependencies": { "call-bind-apply-helpers": "^1.0.1", @@ -5212,23 +5518,10 @@ "node": ">= 0.4" } }, - "node_modules/eastasianwidth": { - "version": "0.2.0", - "resolved": "https://registry.npmjs.org/eastasianwidth/-/eastasianwidth-0.2.0.tgz", - "integrity": "sha512-I88TYZWc9XiYHRQ4/3c5rjjfgkjhLyW2luGIheGERbNQ6OY7yTybanSpDXZa8y7VUP9YmDcYa+eyq4ca7iLqWA==", - "dev": true, - "license": "MIT" - }, "node_modules/ee-first": { "version": "1.1.1", "resolved": "https://registry.npmjs.org/ee-first/-/ee-first-1.1.1.tgz", "integrity": "sha512-WMwm9LhRUo+WUaRN+vRuETqG89IgZphVSNkdFgeb6sS/E4OrDIN7t48CAewSHXc6C8lefD8KKfr5vY61brQlow==", - "license": "MIT" - }, - "node_modules/emoji-regex": { - "version": "9.2.2", - "resolved": "https://registry.npmjs.org/emoji-regex/-/emoji-regex-9.2.2.tgz", - "integrity": "sha512-L18DaJsXSUk2+42pv8mLs5jJT2hqFkFE4j21wOmgbUqsZ2hL72NsUU785g9RXgo3s0ZNgVl42TiHp3ZtOv/Vyg==", "dev": true, "license": "MIT" }, @@ -5236,6 +5529,7 @@ "version": "2.0.0", "resolved": "https://registry.npmjs.org/encodeurl/-/encodeurl-2.0.0.tgz", "integrity": "sha512-Q0n9HRi4m6JuGIV1eFlmvJB7ZEVxu93IrMyiMsGC0lrMJMWzRgx6WGquyfQgZVb31vhGgXnfmPNNXmxnOkRBrg==", + "dev": true, "license": "MIT", "engines": { "node": ">= 0.8" @@ -5272,6 +5566,7 @@ "version": "1.0.1", "resolved": "https://registry.npmjs.org/es-define-property/-/es-define-property-1.0.1.tgz", "integrity": "sha512-e3nRfgfUZ4rNGL232gUgX06QNyyez04KdjFrF+LTRoOXmrOgFKDg4BCdsjW8EnT69eqdYGmRpJwiPVYNrCaW3g==", + "dev": true, "license": "MIT", "engines": { "node": ">= 0.4" @@ -5281,15 +5576,16 @@ "version": "1.3.0", "resolved": "https://registry.npmjs.org/es-errors/-/es-errors-1.3.0.tgz", "integrity": "sha512-Zf5H2Kxt2xjTvbJvP2ZWLEICxA6j+hAmMzIlypy4xcBg1vKVnx89Wy0GbS+kf5cwCVFFzdCFh2XSCFNULS6csw==", + "dev": true, "license": "MIT", "engines": { "node": ">= 0.4" } }, "node_modules/es-module-lexer": { - "version": "1.7.0", - "resolved": "https://registry.npmjs.org/es-module-lexer/-/es-module-lexer-1.7.0.tgz", - "integrity": "sha512-jEQoCwk8hyb2AZziIOLhDqpm5+2ww5uIE6lkO/6jcOCusfk6LhMHpXXfBLXTZ7Ydyt0j4VoUQv6uGNYbdW+kBA==", + "version": "2.1.0", + "resolved": "https://registry.npmjs.org/es-module-lexer/-/es-module-lexer-2.1.0.tgz", + "integrity": "sha512-n27zTYMjYu1aj4MjCWzSP7G9r75utsaoc8m61weK+W8JMBGGQybd43GstCXZ3WNmSFtGT9wi59qQTW6mhTR5LQ==", "dev": true, "license": "MIT" }, @@ -5297,6 +5593,7 @@ "version": "1.1.1", "resolved": "https://registry.npmjs.org/es-object-atoms/-/es-object-atoms-1.1.1.tgz", "integrity": "sha512-FGgH2h8zKNim9ljj7dankFPcICIK9Cp5bm+c2gQSYePhpaG5+esrLODihIorn+Pe6FGJzWhXQotPv73jTaldXA==", + "dev": true, "license": "MIT", "dependencies": { "es-errors": "^1.3.0" @@ -5309,6 +5606,7 @@ "version": "1.46.1", "resolved": "https://registry.npmjs.org/es-toolkit/-/es-toolkit-1.46.1.tgz", "integrity": "sha512-5eNtXOs3tbfxXOj04tjjseeWkRWaoCjdEI+96DgwzZoe6c9juL49pXlzAFTI72aWC9Y8p7168g6XIKjh7k6pyQ==", + "dev": true, "license": "MIT", "workspaces": [ "docs", @@ -5361,6 +5659,7 @@ "version": "1.0.3", "resolved": "https://registry.npmjs.org/escape-html/-/escape-html-1.0.3.tgz", "integrity": "sha512-NiSupZ4OeuGwr68lGIeym/ksIZMJodUGOSCZ/FSnTxcrekbvqrgdUxlJOMpijaKZVjAJrWrGs/6Jy8OMuyj9ow==", + "dev": true, "license": "MIT" }, "node_modules/escape-string-regexp": { @@ -5534,6 +5833,7 @@ "version": "1.2.2", "resolved": "https://registry.npmjs.org/esm-env/-/esm-env-1.2.2.tgz", "integrity": "sha512-Epxrv+Nr/CaL4ZcFGPJIYLWFom+YeV1DqMLHJoEd9SYRxNbaFruBwfEX/kkHUJf55j2+TUbmDcmuilbP1TmXHA==", + "dev": true, "license": "MIT" }, "node_modules/espree": { @@ -5638,6 +5938,7 @@ "version": "1.8.1", "resolved": "https://registry.npmjs.org/etag/-/etag-1.8.1.tgz", "integrity": "sha512-aIL5Fx7mawVa300al2BnEE4iNvo1qETxLrPI/o05L7z6go7fCw1J6EQmbK4FmJ2AS7kgVF/KEZWufBfdClMcPg==", + "dev": true, "license": "MIT", "engines": { "node": ">= 0.6" @@ -5654,6 +5955,7 @@ "version": "3.0.7", "resolved": "https://registry.npmjs.org/eventsource/-/eventsource-3.0.7.tgz", "integrity": "sha512-CRT1WTyuQoD771GW56XEZFQ/ZoSfWid1alKGDYMmkt2yl8UXrVR4pspqWNEcqKvVIzg6PAltWjxcSSPrboA4iA==", + "dev": true, "license": "MIT", "dependencies": { "eventsource-parser": "^3.0.1" @@ -5666,15 +5968,16 @@ "version": "3.0.6", "resolved": "https://registry.npmjs.org/eventsource-parser/-/eventsource-parser-3.0.6.tgz", "integrity": "sha512-Vo1ab+QXPzZ4tCa8SwIHJFaSzy4R6SHf7BY79rFBDf0idraZWAkYrDjDj8uWaSm3S2TK+hJ7/t1CEmZ7jXw+pg==", + "dev": true, "license": "MIT", "engines": { "node": ">=18.0.0" } }, "node_modules/expect-type": { - "version": "1.2.2", - "resolved": "https://registry.npmjs.org/expect-type/-/expect-type-1.2.2.tgz", - "integrity": "sha512-JhFGDVJ7tmDJItKhYgJCGLOWjuK9vPxiXoUFLwLDc99NlmklilbiQJwoctZtt13+xMw91MCk/REan6MWHqDjyA==", + "version": "1.3.0", + "resolved": "https://registry.npmjs.org/expect-type/-/expect-type-1.3.0.tgz", + "integrity": "sha512-knvyeauYhqjOYvQ66MznSMs83wmHrCycNEN6Ao+2AeYEfxUIkuiVxdEa1qlGEPK+We3n0THiDciYSsCcgW/DoA==", "dev": true, "license": "Apache-2.0", "engines": { @@ -5685,6 +5988,7 @@ "version": "5.2.1", "resolved": "https://registry.npmjs.org/express/-/express-5.2.1.tgz", "integrity": "sha512-hIS4idWWai69NezIdRt2xFVofaF4j+6INOpJlVOLDO8zXGpUVEVzIYk12UUi2JzjEzWL3IOAxcTubgz9Po0yXw==", + "dev": true, "license": "MIT", "dependencies": { "accepts": "^2.0.0", @@ -5728,6 +6032,7 @@ "version": "8.5.2", "resolved": "https://registry.npmjs.org/express-rate-limit/-/express-rate-limit-8.5.2.tgz", "integrity": "sha512-5Kb34ipNX694DH48vN9irak1Qx30nb0PLYHXfJgw4YEjiC3ZEmZJhwOp+VfiCYwFzvFTdB9QkArYS5kXa2cx2A==", + "dev": true, "license": "MIT", "dependencies": { "ip-address": "^10.2.0" @@ -5742,25 +6047,18 @@ "express": ">= 4.11" } }, - "node_modules/express/node_modules/cookie": { - "version": "0.7.2", - "resolved": "https://registry.npmjs.org/cookie/-/cookie-0.7.2.tgz", - "integrity": "sha512-yki5XnKuf750l50uGTllt6kKILY4nQ1eNIQatoXEByZ5dWgnKqbnqmTrBE5B4N7lrMJKQ2ytWMiTO2o0v6Ew/w==", - "license": "MIT", - "engines": { - "node": ">= 0.6" - } - }, "node_modules/extend": { "version": "3.0.2", "resolved": "https://registry.npmjs.org/extend/-/extend-3.0.2.tgz", "integrity": "sha512-fjquC59cD7CyW6urNXK0FBufkZcoiGG80wTuPujX590cB5Ttln20E2UB4S/WARVqhXffZl2LNgS+gQdPIIim/g==", + "dev": true, "license": "MIT" }, "node_modules/fast-deep-equal": { "version": "3.1.3", "resolved": "https://registry.npmjs.org/fast-deep-equal/-/fast-deep-equal-3.1.3.tgz", "integrity": "sha512-f3qQ9oQy9j2AhBe/H9VC91wLmKBCCU/gDOnKNAYG5hswO7BLKj09Hc5HYNz9cGI++xlpDCIgDaitVs03ATR84Q==", + "dev": true, "license": "MIT" }, "node_modules/fast-json-stable-stringify": { @@ -5781,6 +6079,7 @@ "version": "3.1.2", "resolved": "https://registry.npmjs.org/fast-uri/-/fast-uri-3.1.2.tgz", "integrity": "sha512-rVjf7ArG3LTk+FS6Yw81V1DLuZl1bRbNrev6Tmd/9RaroeeRRJhAt7jg/6YFxbvAQXUCavSoZhPPj6oOx+5KjQ==", + "dev": true, "funding": [ { "type": "github", @@ -5852,6 +6151,7 @@ "version": "2.1.1", "resolved": "https://registry.npmjs.org/finalhandler/-/finalhandler-2.1.1.tgz", "integrity": "sha512-S8KoZgRZN+a5rNwqTxlZZePjT/4cnm0ROV70LedRHZ0p8u9fRID0hJUZQpkKLzro8LfmC8sx23bY6tVNxv8pQA==", + "dev": true, "license": "MIT", "dependencies": { "debug": "^4.4.0", @@ -5928,27 +6228,11 @@ } } }, - "node_modules/foreground-child": { - "version": "3.3.1", - "resolved": "https://registry.npmjs.org/foreground-child/-/foreground-child-3.3.1.tgz", - "integrity": "sha512-gIXjKqtFuWEgzFRJA9WCQeSJLZDjgJUOMCMzxtvFq/37KojM1BFGufqsCy0r4qSQmYLsZYMeyRqzIWOMup03sw==", - "dev": true, - "license": "ISC", - "dependencies": { - "cross-spawn": "^7.0.6", - "signal-exit": "^4.0.1" - }, - "engines": { - "node": ">=14" - }, - "funding": { - "url": "https://github.com/sponsors/isaacs" - } - }, "node_modules/forwarded": { "version": "0.2.0", "resolved": "https://registry.npmjs.org/forwarded/-/forwarded-0.2.0.tgz", "integrity": "sha512-buRG0fpBtRHSTCOASe6hD258tEubFoRLb4ZNA6NxMVHNw2gOcwHo9wyablzMzOA5z9xA9L1KNjk/Nt6MT9aYow==", + "dev": true, "license": "MIT", "engines": { "node": ">= 0.6" @@ -5958,6 +6242,7 @@ "version": "2.0.0", "resolved": "https://registry.npmjs.org/fresh/-/fresh-2.0.0.tgz", "integrity": "sha512-Rx/WycZ60HOaqLKAi6cHRKKI7zxWbJ31MhntmtwMoaTeF7XFH9hhBp8vITaMidfljRQ6eYWCKkaTK+ykVJHP2A==", + "dev": true, "license": "MIT", "engines": { "node": ">= 0.8" @@ -5982,6 +6267,7 @@ "version": "1.1.2", "resolved": "https://registry.npmjs.org/function-bind/-/function-bind-1.1.2.tgz", "integrity": "sha512-7XHNxH7qX9xG5mIwxkhumTox/MIRNcOgDrxWsMt2pAr23WHp6MrRlN7FBSFpCpr+oVO0F744iUgR82nJMfG2SA==", + "dev": true, "license": "MIT", "funding": { "url": "https://github.com/sponsors/ljharb" @@ -5991,6 +6277,7 @@ "version": "1.3.0", "resolved": "https://registry.npmjs.org/get-intrinsic/-/get-intrinsic-1.3.0.tgz", "integrity": "sha512-9fSjSaos/fRIVIp+xSJlE6lfwhES7LNtKaCBIamHsjr2na1BiABJPo0mOjjz8GJDURarmCPGqaiVg5mfjb98CQ==", + "dev": true, "license": "MIT", "dependencies": { "call-bind-apply-helpers": "^1.0.2", @@ -6015,6 +6302,7 @@ "version": "1.0.1", "resolved": "https://registry.npmjs.org/get-proto/-/get-proto-1.0.1.tgz", "integrity": "sha512-sTSfBjoXBp89JvIKIefqw7U2CCebsc74kiY6awiGogKtoSGbgjYE/G/+l9sF3MWFPNc9IcoOC4ODfKHfxFmp0g==", + "dev": true, "license": "MIT", "dependencies": { "dunder-proto": "^1.0.1", @@ -6024,27 +6312,6 @@ "node": ">= 0.4" } }, - "node_modules/glob": { - "version": "10.5.0", - "resolved": "https://registry.npmjs.org/glob/-/glob-10.5.0.tgz", - "integrity": "sha512-DfXN8DfhJ7NH3Oe7cFmu3NCu1wKbkReJ8TorzSAFbSKrlNaQSKfIzqYqVY8zlbs2NLBbWpRiU52GX2PbaBVNkg==", - "dev": true, - "license": "ISC", - "dependencies": { - "foreground-child": "^3.1.0", - "jackspeak": "^3.1.2", - "minimatch": "^9.0.4", - "minipass": "^7.1.2", - "package-json-from-dist": "^1.0.0", - "path-scurry": "^1.11.1" - }, - "bin": { - "glob": "dist/esm/bin.mjs" - }, - "funding": { - "url": "https://github.com/sponsors/isaacs" - } - }, "node_modules/glob-parent": { "version": "6.0.2", "resolved": "https://registry.npmjs.org/glob-parent/-/glob-parent-6.0.2.tgz", @@ -6058,32 +6325,6 @@ "node": ">=10.13.0" } }, - "node_modules/glob/node_modules/brace-expansion": { - "version": "2.0.3", - "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-2.0.3.tgz", - "integrity": "sha512-MCV/fYJEbqx68aE58kv2cA/kiky1G8vux3OR6/jbS+jIMe/6fJWa0DTzJU7dqijOWYwHi1t29FlfYI9uytqlpA==", - "dev": true, - "license": "MIT", - "dependencies": { - "balanced-match": "^1.0.0" - } - }, - "node_modules/glob/node_modules/minimatch": { - "version": "9.0.9", - "resolved": "https://registry.npmjs.org/minimatch/-/minimatch-9.0.9.tgz", - "integrity": "sha512-OBwBN9AL4dqmETlpS2zasx+vTeWclWzkblfZk7KTA5j3jeOONz/tRCnZomUyvNg83wL5Zv9Ss6HMJXAgL8R2Yg==", - "dev": true, - "license": "ISC", - "dependencies": { - "brace-expansion": "^2.0.2" - }, - "engines": { - "node": ">=16 || 14 >=14.17" - }, - "funding": { - "url": "https://github.com/sponsors/isaacs" - } - }, "node_modules/globals": { "version": "16.3.0", "resolved": "https://registry.npmjs.org/globals/-/globals-16.3.0.tgz", @@ -6101,6 +6342,7 @@ "version": "1.2.0", "resolved": "https://registry.npmjs.org/gopd/-/gopd-1.2.0.tgz", "integrity": "sha512-ZUKRh6/kUFoAiTAtTYPZJ3hw9wNxx+BIBOijnlG9PnrJsCcSjs1wyyD6vJpaYtgnzDrKYRSqf3OO6Rfa93xsRg==", + "dev": true, "license": "MIT", "engines": { "node": ">= 0.4" @@ -6120,6 +6362,7 @@ "version": "0.5.2", "resolved": "https://registry.npmjs.org/hachure-fill/-/hachure-fill-0.5.2.tgz", "integrity": "sha512-3GKBOn+m2LX9iq+JC1064cSFprJY4jL1jCXTcpnfER5HYE2l/4EfWSGzkPa/ZDBmYI0ZOEj5VHV/eKnPGkHuOg==", + "dev": true, "license": "MIT" }, "node_modules/has-flag": { @@ -6136,6 +6379,7 @@ "version": "1.1.0", "resolved": "https://registry.npmjs.org/has-symbols/-/has-symbols-1.1.0.tgz", "integrity": "sha512-1cDNdwJ2Jaohmb3sg4OmKaMBwuC48sYni5HUw2DvsC8LjGTLK9h+eb1X6RyuOHe4hT0ULCW68iomhjUoKUqlPQ==", + "dev": true, "license": "MIT", "engines": { "node": ">= 0.4" @@ -6148,6 +6392,7 @@ "version": "2.0.2", "resolved": "https://registry.npmjs.org/hasown/-/hasown-2.0.2.tgz", "integrity": "sha512-0hJU9SCPvmMzIBdZFqNPXWa6dqh7WdH0cII9y+CyS8rG3nL48Bclra9HmKhVVUHyPWNH5Y7xDwAB7bfgSjkUMQ==", + "dev": true, "license": "MIT", "dependencies": { "function-bind": "^1.1.2" @@ -6276,6 +6521,7 @@ "version": "3.0.0", "resolved": "https://registry.npmjs.org/hast-util-is-element/-/hast-util-is-element-3.0.0.tgz", "integrity": "sha512-Val9mnv2IWpLbNPqc/pUem+a7Ipj2aHacCwgNfTiK0vJKl0LF+4Ba4+v1oPHFpf3bLYmreq0/l3Gud9S5OH42g==", + "dev": true, "license": "MIT", "dependencies": { "@types/hast": "^3.0.0" @@ -6303,6 +6549,7 @@ "version": "5.0.2", "resolved": "https://registry.npmjs.org/hast-util-sanitize/-/hast-util-sanitize-5.0.2.tgz", "integrity": "sha512-3yTWghByc50aGS7JlGhk61SPenfE/p1oaFeNwkOOyrscaOkMGrcW9+Cy/QAIOBpZxP1yqDIzFMR0+Np0i0+usg==", + "dev": true, "license": "MIT", "dependencies": { "@types/hast": "^3.0.0", @@ -6318,6 +6565,7 @@ "version": "9.0.5", "resolved": "https://registry.npmjs.org/hast-util-to-html/-/hast-util-to-html-9.0.5.tgz", "integrity": "sha512-OguPdidb+fbHQSU4Q4ZiLKnzWo8Wwsf5bZfbvu7//a9oTYoqD/fWpe96NuHkoS9h0ccGOTe0C4NGXdtS0iObOw==", + "dev": true, "license": "MIT", "dependencies": { "@types/hast": "^3.0.0", @@ -6341,12 +6589,14 @@ "version": "3.0.3", "resolved": "https://registry.npmjs.org/@types/unist/-/unist-3.0.3.tgz", "integrity": "sha512-ko/gIFJRv177XgZsZcBwnqJN5x/Gien8qNOn0D5bQU/zAzVf9Zt3BlcUiLqhV9y4ARk0GbT3tnUiPNgnTXzc/Q==", + "dev": true, "license": "MIT" }, "node_modules/hast-util-to-text": { "version": "4.0.2", "resolved": "https://registry.npmjs.org/hast-util-to-text/-/hast-util-to-text-4.0.2.tgz", "integrity": "sha512-KK6y/BN8lbaq654j7JgBydev7wuNMcID54lkRav1P0CaE1e47P72AWWPiGKXTJU271ooYzcvTAn/Zt0REnvc7A==", + "dev": true, "license": "MIT", "dependencies": { "@types/hast": "^3.0.0", @@ -6363,12 +6613,14 @@ "version": "3.0.3", "resolved": "https://registry.npmjs.org/@types/unist/-/unist-3.0.3.tgz", "integrity": "sha512-ko/gIFJRv177XgZsZcBwnqJN5x/Gien8qNOn0D5bQU/zAzVf9Zt3BlcUiLqhV9y4ARk0GbT3tnUiPNgnTXzc/Q==", + "dev": true, "license": "MIT" }, "node_modules/hast-util-whitespace": { "version": "3.0.0", "resolved": "https://registry.npmjs.org/hast-util-whitespace/-/hast-util-whitespace-3.0.0.tgz", "integrity": "sha512-88JUN06ipLwsnv+dVn+OIYOvAuvBMy/Qoi6O7mQHxdPXpjy+Cd6xRkWwux7DKO+4sYILtLBRIKgsdpS2gQc7qw==", + "dev": true, "license": "MIT", "dependencies": { "@types/hast": "^3.0.0" @@ -6410,6 +6662,7 @@ "version": "11.11.1", "resolved": "https://registry.npmjs.org/highlight.js/-/highlight.js-11.11.1.tgz", "integrity": "sha512-Xwwo44whKBVCYoliBQwaPvtd/2tYFkRQtXDWj1nackaV2JPXx3L0+Jvd8/qCJ2p+ML0/XVkJ2q+Mr+UVdpJK5w==", + "dev": true, "license": "BSD-3-Clause", "engines": { "node": ">=12.0.0" @@ -6419,6 +6672,7 @@ "version": "4.12.19", "resolved": "https://registry.npmjs.org/hono/-/hono-4.12.19.tgz", "integrity": "sha512-xa3eYXYXx68XTT4hZ7dRzsXBhaq85ToSrlUJNoR0gwz/1Ap/CNwX47wfvV7pc/xWhjKVVkLT7zBJy8chhNguqQ==", + "dev": true, "license": "MIT", "engines": { "node": ">=16.9.0" @@ -6448,6 +6702,7 @@ "version": "3.0.0", "resolved": "https://registry.npmjs.org/html-void-elements/-/html-void-elements-3.0.0.tgz", "integrity": "sha512-bEqo66MRXsUGxWHV5IP0PUiAWwoEjba4VCzg0LjFJBpchPaTfyfCKTG6bc5F8ucKec3q5y6qOdGyYTSBEvhCrg==", + "dev": true, "license": "MIT", "funding": { "type": "github", @@ -6458,6 +6713,7 @@ "version": "2.0.1", "resolved": "https://registry.npmjs.org/http-errors/-/http-errors-2.0.1.tgz", "integrity": "sha512-4FbRdAX+bSdmo4AUFuS0WNiPz8NgFt+r8ThgNWmlrjQjt1Q7ZR9+zTlce2859x4KSXrwIsaeTqDoKQmtP8pLmQ==", + "dev": true, "license": "MIT", "dependencies": { "depd": "~2.0.0", @@ -6521,6 +6777,7 @@ "version": "0.6.3", "resolved": "https://registry.npmjs.org/iconv-lite/-/iconv-lite-0.6.3.tgz", "integrity": "sha512-4fCk79wshMdzMp2rH06qWrJE4iolqLhCUH+OiuIgU++RB0+94NlDL81atO7GX55uUKueo0txHNtvEyI6D7WdMw==", + "dev": true, "license": "MIT", "dependencies": { "safer-buffer": ">= 2.1.2 < 3.0.0" @@ -6567,6 +6824,7 @@ "version": "4.2.0", "resolved": "https://registry.npmjs.org/import-meta-resolve/-/import-meta-resolve-4.2.0.tgz", "integrity": "sha512-Iqv2fzaTQN28s/FwZAoFq0ZSs/7hMAHJVX+w8PZl3cY19Pxk6jFFalxQoIfW2826i/fDLXv8IiEZRIT0lDuWcg==", + "dev": true, "license": "MIT", "funding": { "type": "github", @@ -6597,18 +6855,21 @@ "version": "2.0.4", "resolved": "https://registry.npmjs.org/inherits/-/inherits-2.0.4.tgz", "integrity": "sha512-k/vGaX4/Yla3WzyMCvTQOXYeIHvqOKtnqBduzTHpzpQZzAskKMhZ2K+EnBiSM9zGSoIFeMpXKxa4dYeZIQqewQ==", + "dev": true, "license": "ISC" }, "node_modules/inline-style-parser": { "version": "0.2.4", "resolved": "https://registry.npmjs.org/inline-style-parser/-/inline-style-parser-0.2.4.tgz", "integrity": "sha512-0aO8FkhNZlj/ZIbNi7Lxxr12obT7cL1moPfE4tg1LkX7LlLfC6DeX4l2ZEud1ukP9jNQyNnfzQVqwbwmAATY4Q==", + "dev": true, "license": "MIT" }, "node_modules/internmap": { "version": "2.0.3", "resolved": "https://registry.npmjs.org/internmap/-/internmap-2.0.3.tgz", "integrity": "sha512-5Hh7Y1wQbvY5ooGgPbDaL5iYLAPzMTUrjMulskHLH6wnv/A+1q5rgEaiuqEjB+oxGXIVZs1FF+R/KPN3ZSQYYg==", + "dev": true, "license": "ISC", "engines": { "node": ">=12" @@ -6618,6 +6879,7 @@ "version": "10.2.0", "resolved": "https://registry.npmjs.org/ip-address/-/ip-address-10.2.0.tgz", "integrity": "sha512-/+S6j4E9AHvW9SWMSEY9Xfy66O5PWvVEJ08O0y5JGyEKQpojb0K0GKpz/v5HJ/G0vi3D2sjGK78119oXZeE0qA==", + "dev": true, "license": "MIT", "engines": { "node": ">= 12" @@ -6627,6 +6889,7 @@ "version": "1.9.1", "resolved": "https://registry.npmjs.org/ipaddr.js/-/ipaddr.js-1.9.1.tgz", "integrity": "sha512-0KI/607xoxSToH7GjN1FfSbLoU0+btTicjsQSWQlh/hZykN8KpmMf7uYwPW3R+akZ6R/w18ZlXSHBYXiYUPO3g==", + "dev": true, "license": "MIT", "engines": { "node": ">= 0.10" @@ -6658,16 +6921,6 @@ "node": ">=0.10.0" } }, - "node_modules/is-fullwidth-code-point": { - "version": "3.0.0", - "resolved": "https://registry.npmjs.org/is-fullwidth-code-point/-/is-fullwidth-code-point-3.0.0.tgz", - "integrity": "sha512-zymm5+u+sCsSWyD9qNaejV3DFvhCKclKdizYaJUuHA83RLjb7nSuGnddCHGv0hk+KY7BMAlsWeK4Ueg6EV6XQg==", - "dev": true, - "license": "MIT", - "engines": { - "node": ">=8" - } - }, "node_modules/is-glob": { "version": "4.0.3", "resolved": "https://registry.npmjs.org/is-glob/-/is-glob-4.0.3.tgz", @@ -6715,6 +6968,7 @@ "version": "4.1.0", "resolved": "https://registry.npmjs.org/is-plain-obj/-/is-plain-obj-4.1.0.tgz", "integrity": "sha512-+Pgi+vMuUNkJyExiMBt5IlFoMyKnr5zhJ4Uspz58WOhBF5QoIZkFyNHIbBAtHwzVAgk5RtndVNsDRN61/mmDqg==", + "dev": true, "license": "MIT", "engines": { "node": ">=12" @@ -6727,6 +6981,7 @@ "version": "4.0.0", "resolved": "https://registry.npmjs.org/is-promise/-/is-promise-4.0.0.tgz", "integrity": "sha512-hvpoI6korhJMnej285dSg6nu1+e6uxs7zG3BYAm5byqDsgJNWwxzM6z6iZiAgQR4TJ30JmBTOwqZUw3WlyH3AQ==", + "dev": true, "license": "MIT" }, "node_modules/is-wsl": { @@ -6749,6 +7004,7 @@ "version": "2.0.0", "resolved": "https://registry.npmjs.org/isexe/-/isexe-2.0.0.tgz", "integrity": "sha512-RHxMLp9lnKHGHRng9QFhRCMbYAcVpn69smSGcq3f36xjgVVWThj4qqLbTLlq7Ssj8B+fIQ1EuCEGI2lKsyQeIw==", + "dev": true, "license": "ISC" }, "node_modules/istanbul-lib-coverage": { @@ -6776,21 +7032,6 @@ "node": ">=10" } }, - "node_modules/istanbul-lib-source-maps": { - "version": "5.0.6", - "resolved": "https://registry.npmjs.org/istanbul-lib-source-maps/-/istanbul-lib-source-maps-5.0.6.tgz", - "integrity": "sha512-yg2d+Em4KizZC5niWhQaIomgf5WlL4vOOjZ5xGCmF8SnPE/mDWWXgvRExdcpCgh9lLRRa1/fSYp2ymmbJ1pI+A==", - "dev": true, - "license": "BSD-3-Clause", - "dependencies": { - "@jridgewell/trace-mapping": "^0.3.23", - "debug": "^4.1.1", - "istanbul-lib-coverage": "^3.0.0" - }, - "engines": { - "node": ">=10" - } - }, "node_modules/istanbul-reports": { "version": "3.2.0", "resolved": "https://registry.npmjs.org/istanbul-reports/-/istanbul-reports-3.2.0.tgz", @@ -6805,22 +7046,6 @@ "node": ">=8" } }, - "node_modules/jackspeak": { - "version": "3.4.3", - "resolved": "https://registry.npmjs.org/jackspeak/-/jackspeak-3.4.3.tgz", - "integrity": "sha512-OGlZQpz2yfahA/Rd1Y8Cd9SIEsqvXkLVoSw/cgwhnhFMDbsQFeZYoJJ7bIZBS9BcamUW96asq/npPWugM+RQBw==", - "dev": true, - "license": "BlueOak-1.0.0", - "dependencies": { - "@isaacs/cliui": "^8.0.2" - }, - "funding": { - "url": "https://github.com/sponsors/isaacs" - }, - "optionalDependencies": { - "@pkgjs/parseargs": "^0.11.0" - } - }, "node_modules/jiti": { "version": "2.4.2", "resolved": "https://registry.npmjs.org/jiti/-/jiti-2.4.2.tgz", @@ -6835,15 +7060,16 @@ "version": "6.1.3", "resolved": "https://registry.npmjs.org/jose/-/jose-6.1.3.tgz", "integrity": "sha512-0TpaTfihd4QMNwrz/ob2Bp7X04yuxJkjRGi4aKmOqwhov54i6u79oCv7T+C7lo70MKH6BesI3vscD1yb/yzKXQ==", + "dev": true, "license": "MIT", "funding": { "url": "https://github.com/sponsors/panva" } }, "node_modules/js-tokens": { - "version": "4.0.0", - "resolved": "https://registry.npmjs.org/js-tokens/-/js-tokens-4.0.0.tgz", - "integrity": "sha512-RdJUflcE3cUzKiMqQgsCu06FPu9UdIJO0beYbPhHN4k6apgJtifcoCtT9bcxOpYBtpD2kCM6Sbzg4CausW/PKQ==", + "version": "10.0.0", + "resolved": "https://registry.npmjs.org/js-tokens/-/js-tokens-10.0.0.tgz", + "integrity": "sha512-lM/UBzQmfJRo9ABXbPWemivdCW8V2G8FHaHdypQaIy523snUjog0W71ayWXTjiR+ixeMyVHN2XcpnTd/liPg/Q==", "dev": true, "license": "MIT" }, @@ -6878,6 +7104,7 @@ "version": "8.0.2", "resolved": "https://registry.npmjs.org/json-schema-typed/-/json-schema-typed-8.0.2.tgz", "integrity": "sha512-fQhoXdcvc3V28x7C7BMs4P5+kNlgUURe2jmUT1T//oBRMDrqy1QPelJimwZGo7Hg9VPV3EQV5Bnq4hbFy2vetA==", + "dev": true, "license": "BSD-2-Clause" }, "node_modules/json-stable-stringify-without-jsonify": { @@ -6904,6 +7131,7 @@ "version": "0.16.47", "resolved": "https://registry.npmjs.org/katex/-/katex-0.16.47.tgz", "integrity": "sha512-Eeo8Ys1doU1z+x8AZsPpQu+p/QcZBI5PeOo7QGQdy2x2m0MU/hYagBbGOmXwr5KVbEfVuWv9LpnQWeehogurjg==", + "dev": true, "funding": [ "https://opencollective.com/katex", "https://github.com/sponsors/katex" @@ -6929,7 +7157,8 @@ "node_modules/khroma": { "version": "2.1.0", "resolved": "https://registry.npmjs.org/khroma/-/khroma-2.1.0.tgz", - "integrity": "sha512-Ls993zuzfayK269Svk9hzpeGUKob/sIgZzyHYdjQoAdQetRKpOLj+k/QQQ/6Qi0Yz65mlROrfd+Ev+1+7dz9Kw==" + "integrity": "sha512-Ls993zuzfayK269Svk9hzpeGUKob/sIgZzyHYdjQoAdQetRKpOLj+k/QQQ/6Qi0Yz65mlROrfd+Ev+1+7dz9Kw==", + "dev": true }, "node_modules/kleur": { "version": "4.1.5", @@ -6952,6 +7181,7 @@ "version": "1.0.2", "resolved": "https://registry.npmjs.org/layout-base/-/layout-base-1.0.2.tgz", "integrity": "sha512-8h2oVEZNktL4BH2JCOI90iD1yXwL6iNW7KcCKT2QZgQJR2vbqDsldCTPRU9NifTCqHZci57XvQQ15YTu+sTYPg==", + "dev": true, "license": "MIT" }, "node_modules/levn": { @@ -7221,6 +7451,7 @@ "version": "3.0.0", "resolved": "https://registry.npmjs.org/locate-character/-/locate-character-3.0.0.tgz", "integrity": "sha512-SW13ws7BjaeJ6p7Q6CO2nchbYEc3X3J6WrmTTDto7yMPqVSZTUyY5Tjbid+Ab8gLnATtygYtiDIJGQRRn2ZOiA==", + "dev": true, "license": "MIT" }, "node_modules/locate-path": { @@ -7243,6 +7474,7 @@ "version": "4.18.1", "resolved": "https://registry.npmjs.org/lodash-es/-/lodash-es-4.18.1.tgz", "integrity": "sha512-J8xewKD/Gk22OZbhpOVSwcs60zhd95ESDwezOFuA3/099925PdHJ7OFHNTGtajL3AlZkykD32HykiMo+BIBI8A==", + "dev": true, "license": "MIT" }, "node_modules/lodash.castarray": { @@ -7270,6 +7502,7 @@ "version": "3.1.0", "resolved": "https://registry.npmjs.org/longest-streak/-/longest-streak-3.1.0.tgz", "integrity": "sha512-9Ri+o0JYgehTaVBBDoMqIl8GXtbWg711O3srftcHhZ0dqnETqLaoIK0x17fUw9rFSlK/0NlsKe0Ahhyl5pXE2g==", + "dev": true, "license": "MIT", "funding": { "type": "github", @@ -7287,6 +7520,7 @@ "version": "3.3.0", "resolved": "https://registry.npmjs.org/lowlight/-/lowlight-3.3.0.tgz", "integrity": "sha512-0JNhgFoPvP6U6lE/UdVsSq99tn6DhjjpAj5MxG49ewd2mOBVtwWYIT8ClyABhq198aXXODMU6Ox8DrGy/CpTZQ==", + "dev": true, "license": "MIT", "dependencies": { "@types/hast": "^3.0.0", @@ -7298,13 +7532,6 @@ "url": "https://github.com/sponsors/wooorm" } }, - "node_modules/lru-cache": { - "version": "10.4.3", - "resolved": "https://registry.npmjs.org/lru-cache/-/lru-cache-10.4.3.tgz", - "integrity": "sha512-JNAzZcXrCt42VGLuYz0zfAzDfAvJWW6AfYlDBQyDV5DClI2m5sAmK+OIO7s59XfsRsWHp02jAJrRadPRGTt6SQ==", - "dev": true, - "license": "ISC" - }, "node_modules/lz-string": { "version": "1.5.0", "resolved": "https://registry.npmjs.org/lz-string/-/lz-string-1.5.0.tgz", @@ -7316,24 +7543,25 @@ } }, "node_modules/magic-string": { - "version": "0.30.17", - "resolved": "https://registry.npmjs.org/magic-string/-/magic-string-0.30.17.tgz", - "integrity": "sha512-sNPKHvyjVf7gyjwS4xGTaW/mCnF8wnjtifKBEhxfZ7E/S8tQ0rssrwGNn6q8JH/ohItJfSQp9mBtQYuTlH5QnA==", + "version": "0.30.21", + "resolved": "https://registry.npmjs.org/magic-string/-/magic-string-0.30.21.tgz", + "integrity": "sha512-vd2F4YUyEXKGcLHoq+TEyCjxueSeHnFxyyjNp80yg0XV4vUhnDer/lvvlqM/arB5bXQN5K2/3oinyCRyx8T2CQ==", + "dev": true, "license": "MIT", "dependencies": { - "@jridgewell/sourcemap-codec": "^1.5.0" + "@jridgewell/sourcemap-codec": "^1.5.5" } }, "node_modules/magicast": { - "version": "0.3.5", - "resolved": "https://registry.npmjs.org/magicast/-/magicast-0.3.5.tgz", - "integrity": "sha512-L0WhttDl+2BOsybvEOLK7fW3UA0OQ0IQ2d6Zl2x/a6vVRs3bAY0ECOSHHeL5jD+SbOpOCUEi0y1DgHEn9Qn1AQ==", + "version": "0.5.3", + "resolved": "https://registry.npmjs.org/magicast/-/magicast-0.5.3.tgz", + "integrity": "sha512-pVKE4UdSQ7DvHzivsCIFx2BJn1mHG6KsyrFcaxFx6tONdneEuThrDx0Cj3AMg58KyN4pzYT+LHOotxDQDjNvkw==", "dev": true, "license": "MIT", "dependencies": { - "@babel/parser": "^7.25.4", - "@babel/types": "^7.25.4", - "source-map-js": "^1.2.0" + "@babel/parser": "^7.29.3", + "@babel/types": "^7.29.0", + "source-map-js": "^1.2.1" } }, "node_modules/make-dir": { @@ -7356,6 +7584,7 @@ "version": "3.0.4", "resolved": "https://registry.npmjs.org/markdown-table/-/markdown-table-3.0.4.tgz", "integrity": "sha512-wiYz4+JrLyb/DqW2hkFJxP7Vd7JuTDm77fvbM8VfEQdmSMqcImWeeRbHwZjBjIFki/VaMK2BhFi7oUUZeM5bqw==", + "dev": true, "license": "MIT", "funding": { "type": "github", @@ -7366,6 +7595,7 @@ "version": "16.4.2", "resolved": "https://registry.npmjs.org/marked/-/marked-16.4.2.tgz", "integrity": "sha512-TI3V8YYWvkVf3KJe1dRkpnjs68JUPyEa5vjKrp1XEEJUAOaQc+Qj+L1qWbPd0SJuAdQkFU0h73sXXqwDYxsiDA==", + "dev": true, "license": "MIT", "bin": { "marked": "bin/marked.js" @@ -7378,6 +7608,7 @@ "version": "1.1.0", "resolved": "https://registry.npmjs.org/math-intrinsics/-/math-intrinsics-1.1.0.tgz", "integrity": "sha512-/IXtbwEk5HTPyEwyKX6hGkYXxM9nbj64B+ilVJnC/R6B0pH5G4V3b0pVbL7DBj4tkhBAppbQUlf6F6Xl9LHu1g==", + "dev": true, "license": "MIT", "engines": { "node": ">= 0.4" @@ -7394,6 +7625,7 @@ "version": "3.0.2", "resolved": "https://registry.npmjs.org/mdast-util-find-and-replace/-/mdast-util-find-and-replace-3.0.2.tgz", "integrity": "sha512-Tmd1Vg/m3Xz43afeNxDIhWRtFZgM2VLyaf4vSTYwudTyeuTneoL3qtWMA5jeLyz/O1vDJmmV4QuScFCA2tBPwg==", + "dev": true, "license": "MIT", "dependencies": { "@types/mdast": "^4.0.0", @@ -7410,6 +7642,7 @@ "version": "5.0.0", "resolved": "https://registry.npmjs.org/escape-string-regexp/-/escape-string-regexp-5.0.0.tgz", "integrity": "sha512-/veY75JbMK4j1yjvuUxuVsiS/hr/4iHs9FTT6cgTexxdE0Ly/glccBAkloH/DofkjRbZU3bnoj38mOmhkZ0lHw==", + "dev": true, "license": "MIT", "engines": { "node": ">=12" @@ -7422,6 +7655,7 @@ "version": "2.0.2", "resolved": "https://registry.npmjs.org/mdast-util-from-markdown/-/mdast-util-from-markdown-2.0.2.tgz", "integrity": "sha512-uZhTV/8NBuw0WHkPTrCqDOl0zVe1BIng5ZtHoDk49ME1qqcjYmmLmOf0gELgcRMxN4w2iuIeVso5/6QymSrgmA==", + "dev": true, "license": "MIT", "dependencies": { "@types/mdast": "^4.0.0", @@ -7446,12 +7680,14 @@ "version": "3.0.3", "resolved": "https://registry.npmjs.org/@types/unist/-/unist-3.0.3.tgz", "integrity": "sha512-ko/gIFJRv177XgZsZcBwnqJN5x/Gien8qNOn0D5bQU/zAzVf9Zt3BlcUiLqhV9y4ARk0GbT3tnUiPNgnTXzc/Q==", + "dev": true, "license": "MIT" }, "node_modules/mdast-util-from-markdown/node_modules/unist-util-stringify-position": { "version": "4.0.0", "resolved": "https://registry.npmjs.org/unist-util-stringify-position/-/unist-util-stringify-position-4.0.0.tgz", "integrity": "sha512-0ASV06AAoKCDkS2+xw5RXJywruurpbC4JZSm7nr7MOt1ojAzvyyaO+UxZf18j8FCF6kmzCZKcAgN/yu2gm2XgQ==", + "dev": true, "license": "MIT", "dependencies": { "@types/unist": "^3.0.0" @@ -7465,6 +7701,7 @@ "version": "3.1.0", "resolved": "https://registry.npmjs.org/mdast-util-gfm/-/mdast-util-gfm-3.1.0.tgz", "integrity": "sha512-0ulfdQOM3ysHhCJ1p06l0b0VKlhU0wuQs3thxZQagjcjPrlFRqY215uZGHHJan9GEAXd9MbfPjFJz+qMkVR6zQ==", + "dev": true, "license": "MIT", "dependencies": { "mdast-util-from-markdown": "^2.0.0", @@ -7484,6 +7721,7 @@ "version": "2.0.1", "resolved": "https://registry.npmjs.org/mdast-util-gfm-autolink-literal/-/mdast-util-gfm-autolink-literal-2.0.1.tgz", "integrity": "sha512-5HVP2MKaP6L+G6YaxPNjuL0BPrq9orG3TsrZ9YXbA3vDw/ACI4MEsnoDpn6ZNm7GnZgtAcONJyPhOP8tNJQavQ==", + "dev": true, "license": "MIT", "dependencies": { "@types/mdast": "^4.0.0", @@ -7501,6 +7739,7 @@ "version": "2.1.0", "resolved": "https://registry.npmjs.org/mdast-util-gfm-footnote/-/mdast-util-gfm-footnote-2.1.0.tgz", "integrity": "sha512-sqpDWlsHn7Ac9GNZQMeUzPQSMzR6Wv0WKRNvQRg0KqHh02fpTz69Qc1QSseNX29bhz1ROIyNyxExfawVKTm1GQ==", + "dev": true, "license": "MIT", "dependencies": { "@types/mdast": "^4.0.0", @@ -7518,6 +7757,7 @@ "version": "2.0.0", "resolved": "https://registry.npmjs.org/mdast-util-gfm-strikethrough/-/mdast-util-gfm-strikethrough-2.0.0.tgz", "integrity": "sha512-mKKb915TF+OC5ptj5bJ7WFRPdYtuHv0yTRxK2tJvi+BDqbkiG7h7u/9SI89nRAYcmap2xHQL9D+QG/6wSrTtXg==", + "dev": true, "license": "MIT", "dependencies": { "@types/mdast": "^4.0.0", @@ -7533,6 +7773,7 @@ "version": "2.0.0", "resolved": "https://registry.npmjs.org/mdast-util-gfm-table/-/mdast-util-gfm-table-2.0.0.tgz", "integrity": "sha512-78UEvebzz/rJIxLvE7ZtDd/vIQ0RHv+3Mh5DR96p7cS7HsBhYIICDBCu8csTNWNO6tBWfqXPWekRuj2FNOGOZg==", + "dev": true, "license": "MIT", "dependencies": { "@types/mdast": "^4.0.0", @@ -7550,6 +7791,7 @@ "version": "2.0.0", "resolved": "https://registry.npmjs.org/mdast-util-gfm-task-list-item/-/mdast-util-gfm-task-list-item-2.0.0.tgz", "integrity": "sha512-IrtvNvjxC1o06taBAVJznEnkiHxLFTzgonUdy8hzFVeDun0uTjxxrRGVaNFqkU1wJR3RBPEfsxmU6jDWPofrTQ==", + "dev": true, "license": "MIT", "dependencies": { "@types/mdast": "^4.0.0", @@ -7586,6 +7828,7 @@ "version": "2.0.0", "resolved": "https://registry.npmjs.org/mdast-util-newline-to-break/-/mdast-util-newline-to-break-2.0.0.tgz", "integrity": "sha512-MbgeFca0hLYIEx/2zGsszCSEJJ1JSCdiY5xQxRcLDDGa8EPvlLPupJ4DSajbMPAnC0je8jfb9TiUATnxxrHUog==", + "dev": true, "license": "MIT", "dependencies": { "@types/mdast": "^4.0.0", @@ -7600,6 +7843,7 @@ "version": "4.1.0", "resolved": "https://registry.npmjs.org/mdast-util-phrasing/-/mdast-util-phrasing-4.1.0.tgz", "integrity": "sha512-TqICwyvJJpBwvGAMZjj4J2n0X8QWp21b9l0o7eXyVJ25YNWYbJDVIyD1bZXE6WtV6RmKJVYmQAKWa0zWOABz2w==", + "dev": true, "license": "MIT", "dependencies": { "@types/mdast": "^4.0.0", @@ -7614,6 +7858,7 @@ "version": "13.2.1", "resolved": "https://registry.npmjs.org/mdast-util-to-hast/-/mdast-util-to-hast-13.2.1.tgz", "integrity": "sha512-cctsq2wp5vTsLIcaymblUriiTcZd0CwWtCbLvrOzYCDZoWyMNV8sZ7krj09FSnsiJi3WVsHLM4k6Dq/yaPyCXA==", + "dev": true, "license": "MIT", "dependencies": { "@types/hast": "^3.0.0", @@ -7635,6 +7880,7 @@ "version": "2.1.2", "resolved": "https://registry.npmjs.org/mdast-util-to-markdown/-/mdast-util-to-markdown-2.1.2.tgz", "integrity": "sha512-xj68wMTvGXVOKonmog6LwyJKrYXZPvlwabaryTjLh9LuvovB/KAH+kvi8Gjj+7rJjsFi23nkUxRQv1KqSroMqA==", + "dev": true, "license": "MIT", "dependencies": { "@types/mdast": "^4.0.0", @@ -7656,12 +7902,14 @@ "version": "3.0.3", "resolved": "https://registry.npmjs.org/@types/unist/-/unist-3.0.3.tgz", "integrity": "sha512-ko/gIFJRv177XgZsZcBwnqJN5x/Gien8qNOn0D5bQU/zAzVf9Zt3BlcUiLqhV9y4ARk0GbT3tnUiPNgnTXzc/Q==", + "dev": true, "license": "MIT" }, "node_modules/mdast-util-to-string": { "version": "4.0.0", "resolved": "https://registry.npmjs.org/mdast-util-to-string/-/mdast-util-to-string-4.0.0.tgz", "integrity": "sha512-0H44vDimn51F0YwvxSJSm0eCDOJTRlmN0R1yBh4HLj9wiV1Dn0QoXGbvFAWj2hSItVTlCmBF1hqKlIyUBVFLPg==", + "dev": true, "license": "MIT", "dependencies": { "@types/mdast": "^4.0.0" @@ -7735,6 +7983,7 @@ "version": "1.1.0", "resolved": "https://registry.npmjs.org/media-typer/-/media-typer-1.1.0.tgz", "integrity": "sha512-aisnrDP4GNe06UcKFnV5bfMNPBUw4jsLGaWwWfnH3v02GnBuXX2MCVn5RbrWo0j3pczUilYblq7fQ7Nw2t5XKw==", + "dev": true, "license": "MIT", "engines": { "node": ">= 0.8" @@ -7744,6 +7993,7 @@ "version": "2.0.0", "resolved": "https://registry.npmjs.org/merge-descriptors/-/merge-descriptors-2.0.0.tgz", "integrity": "sha512-Snk314V5ayFLhp3fkUREub6WtjBfPdCPY1Ln8/8munuLuiYhsABgBVWsozAG+MWMbVEvcdcpbi9R7ww22l9Q3g==", + "dev": true, "license": "MIT", "engines": { "node": ">=18" @@ -7756,6 +8006,7 @@ "version": "11.15.0", "resolved": "https://registry.npmjs.org/mermaid/-/mermaid-11.15.0.tgz", "integrity": "sha512-pTMbcf3rWdtLiYGpmoTjHEpeY8seiy6sR+9nD7LOs8KfUbHE4lOUAprTRqRAcWSQ6MQpdX+YEsxShtGsINtPtw==", + "dev": true, "license": "MIT", "dependencies": { "@braintree/sanitize-url": "^7.1.1", @@ -7785,6 +8036,7 @@ "version": "4.0.2", "resolved": "https://registry.npmjs.org/micromark/-/micromark-4.0.2.tgz", "integrity": "sha512-zpe98Q6kvavpCr1NPVSCMebCKfD7CA2NqZ+rykeNhONIJBpc1tFKt9hucLGwha3jNTNI8lHpctWJWoimVF4PfA==", + "dev": true, "funding": [ { "type": "GitHub Sponsors", @@ -7820,6 +8072,7 @@ "version": "2.0.3", "resolved": "https://registry.npmjs.org/micromark-core-commonmark/-/micromark-core-commonmark-2.0.3.tgz", "integrity": "sha512-RDBrHEMSxVFLg6xvnXmb1Ayr2WzLAWjeSATAoxwKYJV94TeNavgoIdA0a9ytzDSVzBy2YKFK+emCPOEibLeCrg==", + "dev": true, "funding": [ { "type": "GitHub Sponsors", @@ -7854,6 +8107,7 @@ "version": "3.0.0", "resolved": "https://registry.npmjs.org/micromark-extension-gfm/-/micromark-extension-gfm-3.0.0.tgz", "integrity": "sha512-vsKArQsicm7t0z2GugkCKtZehqUm31oeGBV/KVSorWSy8ZlNAv7ytjFhvaryUiCUJYqs+NoE6AFhpQvBTM6Q4w==", + "dev": true, "license": "MIT", "dependencies": { "micromark-extension-gfm-autolink-literal": "^2.0.0", @@ -7874,6 +8128,7 @@ "version": "2.1.0", "resolved": "https://registry.npmjs.org/micromark-extension-gfm-autolink-literal/-/micromark-extension-gfm-autolink-literal-2.1.0.tgz", "integrity": "sha512-oOg7knzhicgQ3t4QCjCWgTmfNhvQbDDnJeVu9v81r7NltNCVmhPy1fJRX27pISafdjL+SVc4d3l48Gb6pbRypw==", + "dev": true, "license": "MIT", "dependencies": { "micromark-util-character": "^2.0.0", @@ -7890,6 +8145,7 @@ "version": "2.1.0", "resolved": "https://registry.npmjs.org/micromark-extension-gfm-footnote/-/micromark-extension-gfm-footnote-2.1.0.tgz", "integrity": "sha512-/yPhxI1ntnDNsiHtzLKYnE3vf9JZ6cAisqVDauhp4CEHxlb4uoOTxOCJ+9s51bIB8U1N1FJ1RXOKTIlD5B/gqw==", + "dev": true, "license": "MIT", "dependencies": { "devlop": "^1.0.0", @@ -7910,6 +8166,7 @@ "version": "2.1.0", "resolved": "https://registry.npmjs.org/micromark-extension-gfm-strikethrough/-/micromark-extension-gfm-strikethrough-2.1.0.tgz", "integrity": "sha512-ADVjpOOkjz1hhkZLlBiYA9cR2Anf8F4HqZUO6e5eDcPQd0Txw5fxLzzxnEkSkfnD0wziSGiv7sYhk/ktvbf1uw==", + "dev": true, "license": "MIT", "dependencies": { "devlop": "^1.0.0", @@ -7928,6 +8185,7 @@ "version": "2.1.1", "resolved": "https://registry.npmjs.org/micromark-extension-gfm-table/-/micromark-extension-gfm-table-2.1.1.tgz", "integrity": "sha512-t2OU/dXXioARrC6yWfJ4hqB7rct14e8f7m0cbI5hUmDyyIlwv5vEtooptH8INkbLzOatzKuVbQmAYcbWoyz6Dg==", + "dev": true, "license": "MIT", "dependencies": { "devlop": "^1.0.0", @@ -7945,6 +8203,7 @@ "version": "2.0.0", "resolved": "https://registry.npmjs.org/micromark-extension-gfm-tagfilter/-/micromark-extension-gfm-tagfilter-2.0.0.tgz", "integrity": "sha512-xHlTOmuCSotIA8TW1mDIM6X2O1SiX5P9IuDtqGonFhEK0qgRI4yeC6vMxEV2dgyr2TiD+2PQ10o+cOhdVAcwfg==", + "dev": true, "license": "MIT", "dependencies": { "micromark-util-types": "^2.0.0" @@ -7958,6 +8217,7 @@ "version": "2.1.0", "resolved": "https://registry.npmjs.org/micromark-extension-gfm-task-list-item/-/micromark-extension-gfm-task-list-item-2.1.0.tgz", "integrity": "sha512-qIBZhqxqI6fjLDYFTBIa4eivDMnP+OZqsNwmQ3xNLE4Cxwc+zfQEfbs6tzAo2Hjq+bh6q5F+Z8/cksrLFYWQQw==", + "dev": true, "license": "MIT", "dependencies": { "devlop": "^1.0.0", @@ -7995,6 +8255,7 @@ "version": "2.0.1", "resolved": "https://registry.npmjs.org/micromark-factory-destination/-/micromark-factory-destination-2.0.1.tgz", "integrity": "sha512-Xe6rDdJlkmbFRExpTOmRj9N3MaWmbAgdpSrBQvCFqhezUn4AHqJHbaEnfbVYYiexVSs//tqOdY/DxhjdCiJnIA==", + "dev": true, "funding": [ { "type": "GitHub Sponsors", @@ -8016,6 +8277,7 @@ "version": "2.0.1", "resolved": "https://registry.npmjs.org/micromark-factory-label/-/micromark-factory-label-2.0.1.tgz", "integrity": "sha512-VFMekyQExqIW7xIChcXn4ok29YE3rnuyveW3wZQWWqF4Nv9Wk5rgJ99KzPvHjkmPXF93FXIbBp6YdW3t71/7Vg==", + "dev": true, "funding": [ { "type": "GitHub Sponsors", @@ -8038,6 +8300,7 @@ "version": "2.0.1", "resolved": "https://registry.npmjs.org/micromark-factory-space/-/micromark-factory-space-2.0.1.tgz", "integrity": "sha512-zRkxjtBxxLd2Sc0d+fbnEunsTj46SWXgXciZmHq0kDYGnck/ZSGj9/wULTV95uoeYiK5hRXP2mJ98Uo4cq/LQg==", + "dev": true, "funding": [ { "type": "GitHub Sponsors", @@ -8058,6 +8321,7 @@ "version": "2.0.1", "resolved": "https://registry.npmjs.org/micromark-factory-title/-/micromark-factory-title-2.0.1.tgz", "integrity": "sha512-5bZ+3CjhAd9eChYTHsjy6TGxpOFSKgKKJPJxr293jTbfry2KDoWkhBb6TcPVB4NmzaPhMs1Frm9AZH7OD4Cjzw==", + "dev": true, "funding": [ { "type": "GitHub Sponsors", @@ -8080,6 +8344,7 @@ "version": "2.0.1", "resolved": "https://registry.npmjs.org/micromark-factory-whitespace/-/micromark-factory-whitespace-2.0.1.tgz", "integrity": "sha512-Ob0nuZ3PKt/n0hORHyvoD9uZhr+Za8sFoP+OnMcnWK5lngSzALgQYKMr9RJVOWLqQYuyn6ulqGWSXdwf6F80lQ==", + "dev": true, "funding": [ { "type": "GitHub Sponsors", @@ -8102,6 +8367,7 @@ "version": "2.1.1", "resolved": "https://registry.npmjs.org/micromark-util-character/-/micromark-util-character-2.1.1.tgz", "integrity": "sha512-wv8tdUTJ3thSFFFJKtpYKOYiGP2+v96Hvk4Tu8KpCAsTMs6yi+nVmGh1syvSCsaxz45J6Jbw+9DD6g97+NV67Q==", + "dev": true, "funding": [ { "type": "GitHub Sponsors", @@ -8122,6 +8388,7 @@ "version": "2.0.1", "resolved": "https://registry.npmjs.org/micromark-util-chunked/-/micromark-util-chunked-2.0.1.tgz", "integrity": "sha512-QUNFEOPELfmvv+4xiNg2sRYeS/P84pTW0TCgP5zc9FpXetHY0ab7SxKyAQCNCc1eK0459uoLI1y5oO5Vc1dbhA==", + "dev": true, "funding": [ { "type": "GitHub Sponsors", @@ -8141,6 +8408,7 @@ "version": "2.0.1", "resolved": "https://registry.npmjs.org/micromark-util-classify-character/-/micromark-util-classify-character-2.0.1.tgz", "integrity": "sha512-K0kHzM6afW/MbeWYWLjoHQv1sgg2Q9EccHEDzSkxiP/EaagNzCm7T/WMKZ3rjMbvIpvBiZgwR3dKMygtA4mG1Q==", + "dev": true, "funding": [ { "type": "GitHub Sponsors", @@ -8162,6 +8430,7 @@ "version": "2.0.1", "resolved": "https://registry.npmjs.org/micromark-util-combine-extensions/-/micromark-util-combine-extensions-2.0.1.tgz", "integrity": "sha512-OnAnH8Ujmy59JcyZw8JSbK9cGpdVY44NKgSM7E9Eh7DiLS2E9RNQf0dONaGDzEG9yjEl5hcqeIsj4hfRkLH/Bg==", + "dev": true, "funding": [ { "type": "GitHub Sponsors", @@ -8182,6 +8451,7 @@ "version": "2.0.2", "resolved": "https://registry.npmjs.org/micromark-util-decode-numeric-character-reference/-/micromark-util-decode-numeric-character-reference-2.0.2.tgz", "integrity": "sha512-ccUbYk6CwVdkmCQMyr64dXz42EfHGkPQlBj5p7YVGzq8I7CtjXZJrubAYezf7Rp+bjPseiROqe7G6foFd+lEuw==", + "dev": true, "funding": [ { "type": "GitHub Sponsors", @@ -8201,6 +8471,7 @@ "version": "2.0.1", "resolved": "https://registry.npmjs.org/micromark-util-decode-string/-/micromark-util-decode-string-2.0.1.tgz", "integrity": "sha512-nDV/77Fj6eH1ynwscYTOsbK7rR//Uj0bZXBwJZRfaLEJ1iGBR6kIfNmlNqaqJf649EP0F3NWNdeJi03elllNUQ==", + "dev": true, "funding": [ { "type": "GitHub Sponsors", @@ -8223,6 +8494,7 @@ "version": "2.0.1", "resolved": "https://registry.npmjs.org/micromark-util-encode/-/micromark-util-encode-2.0.1.tgz", "integrity": "sha512-c3cVx2y4KqUnwopcO9b/SCdo2O67LwJJ/UyqGfbigahfegL9myoEFoDYZgkT7f36T0bLrM9hZTAaAyH+PCAXjw==", + "dev": true, "funding": [ { "type": "GitHub Sponsors", @@ -8239,6 +8511,7 @@ "version": "2.0.1", "resolved": "https://registry.npmjs.org/micromark-util-html-tag-name/-/micromark-util-html-tag-name-2.0.1.tgz", "integrity": "sha512-2cNEiYDhCWKI+Gs9T0Tiysk136SnR13hhO8yW6BGNyhOC4qYFnwF1nKfD3HFAIXA5c45RrIG1ub11GiXeYd1xA==", + "dev": true, "funding": [ { "type": "GitHub Sponsors", @@ -8255,6 +8528,7 @@ "version": "2.0.1", "resolved": "https://registry.npmjs.org/micromark-util-normalize-identifier/-/micromark-util-normalize-identifier-2.0.1.tgz", "integrity": "sha512-sxPqmo70LyARJs0w2UclACPUUEqltCkJ6PhKdMIDuJ3gSf/Q+/GIe3WKl0Ijb/GyH9lOpUkRAO2wp0GVkLvS9Q==", + "dev": true, "funding": [ { "type": "GitHub Sponsors", @@ -8274,6 +8548,7 @@ "version": "2.0.1", "resolved": "https://registry.npmjs.org/micromark-util-resolve-all/-/micromark-util-resolve-all-2.0.1.tgz", "integrity": "sha512-VdQyxFWFT2/FGJgwQnJYbe1jjQoNTS4RjglmSjTUlpUMa95Htx9NHeYW4rGDJzbjvCsl9eLjMQwGeElsqmzcHg==", + "dev": true, "funding": [ { "type": "GitHub Sponsors", @@ -8293,6 +8568,7 @@ "version": "2.0.1", "resolved": "https://registry.npmjs.org/micromark-util-sanitize-uri/-/micromark-util-sanitize-uri-2.0.1.tgz", "integrity": "sha512-9N9IomZ/YuGGZZmQec1MbgxtlgougxTodVwDzzEouPKo3qFWvymFHWcnDi2vzV1ff6kas9ucW+o3yzJK9YB1AQ==", + "dev": true, "funding": [ { "type": "GitHub Sponsors", @@ -8314,6 +8590,7 @@ "version": "2.1.0", "resolved": "https://registry.npmjs.org/micromark-util-subtokenize/-/micromark-util-subtokenize-2.1.0.tgz", "integrity": "sha512-XQLu552iSctvnEcgXw6+Sx75GflAPNED1qx7eBJ+wydBb2KCbRZe+NwvIEEMM83uml1+2WSXpBAcp9IUCgCYWA==", + "dev": true, "funding": [ { "type": "GitHub Sponsors", @@ -8336,6 +8613,7 @@ "version": "2.0.1", "resolved": "https://registry.npmjs.org/micromark-util-symbol/-/micromark-util-symbol-2.0.1.tgz", "integrity": "sha512-vs5t8Apaud9N28kgCrRUdEed4UJ+wWNvicHLPxCa9ENlYuAY31M0ETy5y1vA33YoNPDFTghEbnh6efaE8h4x0Q==", + "dev": true, "funding": [ { "type": "GitHub Sponsors", @@ -8352,6 +8630,7 @@ "version": "2.0.2", "resolved": "https://registry.npmjs.org/micromark-util-types/-/micromark-util-types-2.0.2.tgz", "integrity": "sha512-Yw0ECSpJoViF1qTU4DC6NwtC4aWGt1EkzaQB8KPPyCRR8z9TWeV0HbEFGTO+ZY1wB22zmxnJqhPyTpOVCpeHTA==", + "dev": true, "funding": [ { "type": "GitHub Sponsors", @@ -8410,6 +8689,7 @@ "version": "1.54.0", "resolved": "https://registry.npmjs.org/mime-db/-/mime-db-1.54.0.tgz", "integrity": "sha512-aU5EJuIN2WDemCcAp2vFBfp/m4EAhWJnUNSSw0ixs7/kXbd6Pg64EmwJkNdFhB8aWt1sH2CTXrLxo/iAGV3oPQ==", + "dev": true, "license": "MIT", "engines": { "node": ">= 0.6" @@ -8419,6 +8699,7 @@ "version": "3.0.2", "resolved": "https://registry.npmjs.org/mime-types/-/mime-types-3.0.2.tgz", "integrity": "sha512-Lbgzdk0h4juoQ9fCKXW4by0UJqj+nOOrI9MJ1sSj4nI8aI2eo1qmvQEie4VD1glsS250n15LsWsYtCugiStS5A==", + "dev": true, "license": "MIT", "dependencies": { "mime-db": "^1.54.0" @@ -8501,6 +8782,7 @@ "version": "1.1.0", "resolved": "https://registry.npmjs.org/mode-watcher/-/mode-watcher-1.1.0.tgz", "integrity": "sha512-mUT9RRGPDYenk59qJauN1rhsIMKBmWA3xMF+uRwE8MW/tjhaDSCCARqkSuDTq8vr4/2KcAxIGVjACxTjdk5C3g==", + "dev": true, "license": "MIT", "dependencies": { "runed": "^0.25.0", @@ -8534,6 +8816,7 @@ "version": "2.1.3", "resolved": "https://registry.npmjs.org/ms/-/ms-2.1.3.tgz", "integrity": "sha512-6FlzubTLZG3J2a/NVCAleEhjzq5oxgHyaCU9yYXvcLsvoVaHJq/s5xXI6/XXP6tz7R9xAOtHnSO/tXtF3WRTlA==", + "dev": true, "license": "MIT" }, "node_modules/nanoid": { @@ -8566,6 +8849,7 @@ "version": "1.0.0", "resolved": "https://registry.npmjs.org/negotiator/-/negotiator-1.0.0.tgz", "integrity": "sha512-8Ofs/AUQh8MaEcrlq5xOX0CQ9ypTF5dl78mjlMNfOK08fzpgTHQRQPBxcPlEtIw0yRpws+Zo/3r+5WRby7u3Gg==", + "dev": true, "license": "MIT", "engines": { "node": ">= 0.6" @@ -8583,6 +8867,7 @@ "version": "4.1.1", "resolved": "https://registry.npmjs.org/object-assign/-/object-assign-4.1.1.tgz", "integrity": "sha512-rJgTQnkUnH1sFw8yT6VSU3zD3sWmu6sZhIseY8VX+GRu3P6F7Fu+JNDoXfklElbLJSnc3FUQHVe4cU5hj+BcUg==", + "dev": true, "license": "MIT", "engines": { "node": ">=0.10.0" @@ -8592,6 +8877,7 @@ "version": "1.13.4", "resolved": "https://registry.npmjs.org/object-inspect/-/object-inspect-1.13.4.tgz", "integrity": "sha512-W67iLl4J2EXEGTbfeHCffrjDfitvLANg0UlX3wFUUSTx92KXRFegMHUVgSqE+wvhAbi4WqjGg9czysTV2Epbew==", + "dev": true, "license": "MIT", "engines": { "node": ">= 0.4" @@ -8600,10 +8886,25 @@ "url": "https://github.com/sponsors/ljharb" } }, + "node_modules/obug": { + "version": "2.1.2", + "resolved": "https://registry.npmjs.org/obug/-/obug-2.1.2.tgz", + "integrity": "sha512-AWGB9WFcRXOQs48Z/udjI5ZcZMHXwX8XPByNpOydgcGsDLIzjGizhoMWJyKAWze7AVW/2W1i+/gPX4YtKe5cyg==", + "dev": true, + "funding": [ + "https://github.com/sponsors/sxzz", + "https://opencollective.com/debug" + ], + "license": "MIT", + "engines": { + "node": ">=12.20.0" + } + }, "node_modules/on-finished": { "version": "2.4.1", "resolved": "https://registry.npmjs.org/on-finished/-/on-finished-2.4.1.tgz", "integrity": "sha512-oVlzkg3ENAhCk2zdv7IJwd/QUD4z2RxRwpkcGY8psCVcCYZNq4wYnVWALHM+brtuJjePWiYF/ClmuDr8Ch5+kg==", + "dev": true, "license": "MIT", "dependencies": { "ee-first": "1.1.1" @@ -8616,6 +8917,7 @@ "version": "1.4.0", "resolved": "https://registry.npmjs.org/once/-/once-1.4.0.tgz", "integrity": "sha512-lNaJgI+2Q5URQBkccEKHTQOPaXdUxnZZElQTZY0MFUAuaEqe1E+Nyvgdz/aIyNi6Z9MzO5dv1H8n58/GELp3+w==", + "dev": true, "license": "ISC", "dependencies": { "wrappy": "1" @@ -8700,17 +9002,11 @@ "url": "https://github.com/sponsors/sindresorhus" } }, - "node_modules/package-json-from-dist": { - "version": "1.0.1", - "resolved": "https://registry.npmjs.org/package-json-from-dist/-/package-json-from-dist-1.0.1.tgz", - "integrity": "sha512-UEZIS3/by4OC8vL3P2dTXRETpebLI2NiI5vIrjaD/5UtrkFX/tNbwjTSRAGC/+7CAo2pIcBaRgWmcBBHcsaCIw==", - "dev": true, - "license": "BlueOak-1.0.0" - }, "node_modules/package-manager-detector": { "version": "1.6.0", "resolved": "https://registry.npmjs.org/package-manager-detector/-/package-manager-detector-1.6.0.tgz", "integrity": "sha512-61A5ThoTiDG/C8s8UMZwSorAGwMJ0ERVGj2OjoW5pAalsNOg15+iQiPzrLJ4jhZ1HJzmC2PIHT2oEiH3R5fzNA==", + "dev": true, "license": "MIT" }, "node_modules/parent-module": { @@ -8743,6 +9039,7 @@ "version": "1.3.3", "resolved": "https://registry.npmjs.org/parseurl/-/parseurl-1.3.3.tgz", "integrity": "sha512-CiyeOxFT/JZyN5m0z9PfXw4SCBJ6Sygz1Dpl0wqjlhDEGGBP1GnsUVEL0p63hoG1fcj3fHynXi9NYO4nWOL+qQ==", + "dev": true, "license": "MIT", "engines": { "node": ">= 0.8" @@ -8752,6 +9049,7 @@ "version": "0.1.0", "resolved": "https://registry.npmjs.org/path-data-parser/-/path-data-parser-0.1.0.tgz", "integrity": "sha512-NOnmBpt5Y2RWbuv0LMzsayp3lVylAHLPUTut412ZA3l+C4uw4ZVkQbjShYCQ8TCpUMdPapr4YjUqLYD6v68j+w==", + "dev": true, "license": "MIT" }, "node_modules/path-exists": { @@ -8768,32 +9066,17 @@ "version": "3.1.1", "resolved": "https://registry.npmjs.org/path-key/-/path-key-3.1.1.tgz", "integrity": "sha512-ojmeN0qd+y0jszEtoY48r0Peq5dwMEkIlCOu6Q5f41lfkswXuKtYrhgoTpLnyIcHm24Uhqx+5Tqm2InSwLhE6Q==", + "dev": true, "license": "MIT", "engines": { "node": ">=8" } }, - "node_modules/path-scurry": { - "version": "1.11.1", - "resolved": "https://registry.npmjs.org/path-scurry/-/path-scurry-1.11.1.tgz", - "integrity": "sha512-Xa4Nw17FS9ApQFJ9umLiJS4orGjm7ZzwUrwamcGQuHSzDyth9boKDaycYdDcZDuqYATXw4HFXgaqWTctW/v1HA==", - "dev": true, - "license": "BlueOak-1.0.0", - "dependencies": { - "lru-cache": "^10.2.0", - "minipass": "^5.0.0 || ^6.0.2 || ^7.0.0" - }, - "engines": { - "node": ">=16 || 14 >=14.18" - }, - "funding": { - "url": "https://github.com/sponsors/isaacs" - } - }, "node_modules/path-to-regexp": { "version": "8.4.2", "resolved": "https://registry.npmjs.org/path-to-regexp/-/path-to-regexp-8.4.2.tgz", "integrity": "sha512-qRcuIdP69NPm4qbACK+aDogI5CBDMi1jKe0ry5rSQJz8JVLsC7jV8XpiJjGRLLol3N+R5ihGYcrPLTno6pAdBA==", + "dev": true, "license": "MIT", "funding": { "type": "opencollective", @@ -8821,6 +9104,7 @@ "version": "5.4.54", "resolved": "https://registry.npmjs.org/pdfjs-dist/-/pdfjs-dist-5.4.54.tgz", "integrity": "sha512-TBAiTfQw89gU/Z4LW98Vahzd2/LoCFprVGvGbTgFt+QCB1F+woyOPmNNVgLa6djX9Z9GGTnj7qE1UzpOVJiINw==", + "dev": true, "license": "Apache-2.0", "engines": { "node": ">=20.16.0 || >=22.3.0" @@ -8853,6 +9137,7 @@ "version": "5.0.1", "resolved": "https://registry.npmjs.org/pkce-challenge/-/pkce-challenge-5.0.1.tgz", "integrity": "sha512-wQ0b/W4Fr01qtpHlqSqspcj3EhBvimsdh0KlHhH8HRZnMsEa0ea2fTULOXOS9ccQr3om+GcGRk4e+isrZWV8qQ==", + "dev": true, "license": "MIT", "engines": { "node": ">=16.20.0" @@ -8890,16 +9175,28 @@ "node": ">=18" } }, + "node_modules/pngjs": { + "version": "7.0.0", + "resolved": "https://registry.npmjs.org/pngjs/-/pngjs-7.0.0.tgz", + "integrity": "sha512-LKWqWJRhstyYo9pGvgor/ivk2w94eSjE3RGVuzLGlr3NmD8bf7RcYGze1mNdEHRP6TRP6rMuDHk5t44hnTRyow==", + "dev": true, + "license": "MIT", + "engines": { + "node": ">=14.19.0" + } + }, "node_modules/points-on-curve": { "version": "0.2.0", "resolved": "https://registry.npmjs.org/points-on-curve/-/points-on-curve-0.2.0.tgz", "integrity": "sha512-0mYKnYYe9ZcqMCWhUjItv/oHjvgEsfKvnUTg8sAtnHr3GVy7rGkXCb6d5cSyqrWqL4k81b9CPg3urd+T7aop3A==", + "dev": true, "license": "MIT" }, "node_modules/points-on-path": { "version": "0.2.1", "resolved": "https://registry.npmjs.org/points-on-path/-/points-on-path-0.2.1.tgz", "integrity": "sha512-25ClnWWuw7JbWZcgqY/gJ4FQWadKxGWk+3kR/7kD0tCaDtPPMj7oHu2ToLaVhfpnHrZzYby2w6tUA0eOIuUg8g==", + "dev": true, "license": "MIT", "dependencies": { "path-data-parser": "0.1.0", @@ -9187,6 +9484,7 @@ "integrity": "sha512-Qb1gy5OrP5+zDf2Bvnzdl3jsTf1qXVMazbvCoKhtKqVs4/YK4ozX4gKQJJVyNe+cajNPn0KoC0MC3FUmaHWEmQ==", "dev": true, "license": "MIT", + "peer": true, "dependencies": { "ansi-regex": "^5.0.1", "ansi-styles": "^5.0.0", @@ -9202,6 +9500,7 @@ "integrity": "sha512-Cxwpt2SfTzTtXcfOlzGEee8O+c+MmUgGrNiBcXnuWxuFJHe6a5Hz7qwhwe5OgaSYI0IJvkLqWX1ASG+cJOkEiA==", "dev": true, "license": "MIT", + "peer": true, "engines": { "node": ">=10" }, @@ -9230,6 +9529,7 @@ "version": "7.1.0", "resolved": "https://registry.npmjs.org/property-information/-/property-information-7.1.0.tgz", "integrity": "sha512-TwEZ+X+yCJmYfL7TPUOcvBZ4QfoT5YenQiJuX//0th53DE6w0xxLEtfK3iyryQFddXuvkIk51EEgrJQ0WJkOmQ==", + "dev": true, "license": "MIT", "funding": { "type": "github", @@ -9240,6 +9540,7 @@ "version": "2.0.7", "resolved": "https://registry.npmjs.org/proxy-addr/-/proxy-addr-2.0.7.tgz", "integrity": "sha512-llQsMLSUDUPT44jdrU/O37qlnifitDP+ZwrmmZcoSKyLKvtZxpyV0n2/bD/N4tBAAZ/gJEdZU7KMraoK1+XYAg==", + "dev": true, "license": "MIT", "dependencies": { "forwarded": "0.2.0", @@ -9260,9 +9561,10 @@ } }, "node_modules/qs": { - "version": "6.15.0", - "resolved": "https://registry.npmjs.org/qs/-/qs-6.15.0.tgz", - "integrity": "sha512-mAZTtNCeetKMH+pSjrb76NAM8V9a05I9aBZOHztWy/UqcJdQYNsf59vrRKWnojAT9Y+GbIvoTBC++CPHqpDBhQ==", + "version": "6.15.2", + "resolved": "https://registry.npmjs.org/qs/-/qs-6.15.2.tgz", + "integrity": "sha512-Rzq0KEyX/w/tEybncDgdkZrJgVUsUMk3xjh3t5bv3S1HTAtg+uOYt72+ZfwiQwKdysThkTBdL/rTi6HDmX9Ddw==", + "dev": true, "license": "BSD-3-Clause", "dependencies": { "side-channel": "^1.1.0" @@ -9278,6 +9580,7 @@ "version": "1.2.1", "resolved": "https://registry.npmjs.org/range-parser/-/range-parser-1.2.1.tgz", "integrity": "sha512-Hrgsx+orqoygnmhFbKaHE6c296J+HTAQXoxEF6gNupROmmGJRoyzfG3ccAveqCBrwr/2yxQ5BVd/GTl5agOwSg==", + "dev": true, "license": "MIT", "engines": { "node": ">= 0.6" @@ -9287,6 +9590,7 @@ "version": "3.0.2", "resolved": "https://registry.npmjs.org/raw-body/-/raw-body-3.0.2.tgz", "integrity": "sha512-K5zQjDllxWkf7Z5xJdV0/B0WTNqx6vxG70zJE4N0kBs4LovmEYWJzQGxC9bS9RAKu3bgM40lrd5zoLJ12MQ5BA==", + "dev": true, "license": "MIT", "dependencies": { "bytes": "~3.1.2", @@ -9302,6 +9606,7 @@ "version": "0.7.2", "resolved": "https://registry.npmjs.org/iconv-lite/-/iconv-lite-0.7.2.tgz", "integrity": "sha512-im9DjEDQ55s9fL4EYzOAv0yMqmMBSZp6G0VvFyTMPKWxiSBHUj9NW/qqLmXUwXrrM7AvqSlTCfvqRb0cM8yYqw==", + "dev": true, "license": "MIT", "dependencies": { "safer-buffer": ">= 2.1.2 < 3.0.0" @@ -9342,7 +9647,8 @@ "resolved": "https://registry.npmjs.org/react-is/-/react-is-17.0.2.tgz", "integrity": "sha512-w2GsyukL62IJnlaff/nRegPQR94C/XXamvMWmSHRJ4y7Ts/4ocGRmTHvOs8PSE6pB3dWOrD/nueuU5sduBsQ4w==", "dev": true, - "license": "MIT" + "license": "MIT", + "peer": true }, "node_modules/readdirp": { "version": "4.1.2", @@ -9393,6 +9699,7 @@ "version": "7.0.2", "resolved": "https://registry.npmjs.org/rehype-highlight/-/rehype-highlight-7.0.2.tgz", "integrity": "sha512-k158pK7wdC2qL3M5NcZROZ2tR/l7zOzjxXd5VGdcfIyoijjQqpHd3JKtYSBDpDZ38UI2WJWuFAtkMDxmx5kstA==", + "dev": true, "license": "MIT", "dependencies": { "@types/hast": "^3.0.0", @@ -9430,6 +9737,7 @@ "version": "10.0.1", "resolved": "https://registry.npmjs.org/rehype-stringify/-/rehype-stringify-10.0.1.tgz", "integrity": "sha512-k9ecfXHmIPuFVI61B9DeLPN0qFHfawM6RsuX48hoqlaKSF61RskNjSm1lI8PhBEM0MRdLxVVm4WmTqJQccH9mA==", + "dev": true, "license": "MIT", "dependencies": { "@types/hast": "^3.0.0", @@ -9445,6 +9753,7 @@ "version": "15.0.1", "resolved": "https://registry.npmjs.org/remark/-/remark-15.0.1.tgz", "integrity": "sha512-Eht5w30ruCXgFmxVUSlNWQ9iiimq07URKeFS3hNc8cUWy1llX4KDWfyEDZRycMc+znsN9Ux5/tJ/BFdgdOwA3A==", + "dev": true, "license": "MIT", "dependencies": { "@types/mdast": "^4.0.0", @@ -9461,6 +9770,7 @@ "version": "4.0.0", "resolved": "https://registry.npmjs.org/remark-breaks/-/remark-breaks-4.0.0.tgz", "integrity": "sha512-IjEjJOkH4FuJvHZVIW0QCDWxcG96kCq7An/KVH2NfJe6rKZU2AsHeB3OEjPNRxi4QC34Xdx7I2KGYn6IpT7gxQ==", + "dev": true, "license": "MIT", "dependencies": { "@types/mdast": "^4.0.0", @@ -9476,6 +9786,7 @@ "version": "4.0.1", "resolved": "https://registry.npmjs.org/remark-gfm/-/remark-gfm-4.0.1.tgz", "integrity": "sha512-1quofZ2RQ9EWdeN34S79+KExV1764+wCUGop5CPL1WGdD0ocPpu91lzPGbwWMECpEpd42kJGQwzRfyov9j4yNg==", + "dev": true, "license": "MIT", "dependencies": { "@types/mdast": "^4.0.0", @@ -9494,6 +9805,7 @@ "version": "16.0.1", "resolved": "https://registry.npmjs.org/remark-html/-/remark-html-16.0.1.tgz", "integrity": "sha512-B9JqA5i0qZe0Nsf49q3OXyGvyXuZFDzAP2iOFLEumymuYJITVpiH1IgsTEwTpdptDmZlMDMWeDmSawdaJIGCXQ==", + "dev": true, "license": "MIT", "dependencies": { "@types/mdast": "^4.0.0", @@ -9528,6 +9840,7 @@ "version": "11.0.0", "resolved": "https://registry.npmjs.org/remark-parse/-/remark-parse-11.0.0.tgz", "integrity": "sha512-FCxlKLNGknS5ba/1lmpYijMUzX2esxW5xQqjWxw2eHFfS2MSdaHVINFmhjo+qN1WhZhNimq0dZATN9pH0IDrpA==", + "dev": true, "license": "MIT", "dependencies": { "@types/mdast": "^4.0.0", @@ -9544,6 +9857,7 @@ "version": "11.1.2", "resolved": "https://registry.npmjs.org/remark-rehype/-/remark-rehype-11.1.2.tgz", "integrity": "sha512-Dh7l57ianaEoIpzbp0PC9UKAdCSVklD8E5Rpw7ETfbTl3FqcOOgq5q2LVDhgGCkaBv7p24JXikPdvhhmHvKMsw==", + "dev": true, "license": "MIT", "dependencies": { "@types/hast": "^3.0.0", @@ -9561,6 +9875,7 @@ "version": "11.0.0", "resolved": "https://registry.npmjs.org/remark-stringify/-/remark-stringify-11.0.0.tgz", "integrity": "sha512-1OSmLd3awB/t8qdoEOMazZkNsfVTeY4fTsgzcQFdXNq8ToTN4ZGwrMnlda4K6smTFKD+GRV6O48i6Z4iKgPPpw==", + "dev": true, "license": "MIT", "dependencies": { "@types/mdast": "^4.0.0", @@ -9576,6 +9891,7 @@ "version": "2.0.2", "resolved": "https://registry.npmjs.org/require-from-string/-/require-from-string-2.0.2.tgz", "integrity": "sha512-Xf0nWe6RseziFMu+Ap9biiUbmplq6S9/p+7w7YXP/JBHhrUDDUhwa+vANyubuqfZWTveU//DYVGsDG7RKL/vEw==", + "dev": true, "license": "MIT", "engines": { "node": ">=0.10.0" @@ -9602,6 +9918,7 @@ "version": "3.0.3", "resolved": "https://registry.npmjs.org/robust-predicates/-/robust-predicates-3.0.3.tgz", "integrity": "sha512-NS3levdsRIUOmiJ8FZWCP7LG3QpJyrs/TE0Zpf1yvZu8cAJJ6QMW92H1c7kWpdIHo8RvmLxN/o2JXTKHp74lUA==", + "dev": true, "license": "Unlicense" }, "node_modules/rollup": { @@ -9653,6 +9970,7 @@ "version": "4.6.6", "resolved": "https://registry.npmjs.org/roughjs/-/roughjs-4.6.6.tgz", "integrity": "sha512-ZUz/69+SYpFN/g/lUlo2FXcIjRkSu3nDarreVdGGndHEBJ6cXPdKguS8JGxwj5HA5xIbVKSmLgr5b3AWxtRfvQ==", + "dev": true, "license": "MIT", "dependencies": { "hachure-fill": "^0.5.2", @@ -9665,6 +9983,7 @@ "version": "2.2.0", "resolved": "https://registry.npmjs.org/router/-/router-2.2.0.tgz", "integrity": "sha512-nLTrUKm2UyiL7rlhapu/Zl45FwNgkZGaCpZbIHajDYgwlJCOzLSk+cIPAnsEqV955GjILJnKbdQC1nVPz+gAYQ==", + "dev": true, "license": "MIT", "dependencies": { "debug": "^4.4.0", @@ -9694,6 +10013,7 @@ "version": "0.25.0", "resolved": "https://registry.npmjs.org/runed/-/runed-0.25.0.tgz", "integrity": "sha512-7+ma4AG9FT2sWQEA0Egf6mb7PBT2vHyuHail1ie8ropfSjvZGtEAx8YTmUjv/APCsdRRxEVvArNjALk9zFSOrg==", + "dev": true, "funding": [ "https://github.com/sponsors/huntabyte", "https://github.com/sponsors/tglide" @@ -9709,6 +10029,7 @@ "version": "1.3.3", "resolved": "https://registry.npmjs.org/rw/-/rw-1.3.3.tgz", "integrity": "sha512-PdhdWy89SiZogBLaw42zdeqtRJ//zFd2PgQavcICDUgJT5oW10QCRKbJ6bg4r0/UY2M6BWd5tkxuGFRvCkgfHQ==", + "dev": true, "license": "BSD-3-Clause" }, "node_modules/sade": { @@ -9735,6 +10056,7 @@ "version": "2.1.2", "resolved": "https://registry.npmjs.org/safer-buffer/-/safer-buffer-2.1.2.tgz", "integrity": "sha512-YZo3K82SD7Riyi0E1EQPojLz7kpepnSQI9IyPbHHg1XXXevb5dJI7tpyN2ADxGcQbHG7vcyRHk0cbwqcQriUtg==", + "dev": true, "license": "MIT" }, "node_modules/sass": { @@ -9796,6 +10118,7 @@ "version": "1.2.1", "resolved": "https://registry.npmjs.org/send/-/send-1.2.1.tgz", "integrity": "sha512-1gnZf7DFcoIcajTjTwjwuDjzuz4PPcY2StKPlsGAQ1+YH20IRVrBaXSWmdjowTJ6u8Rc01PoYOGHXfP1mYcZNQ==", + "dev": true, "license": "MIT", "dependencies": { "debug": "^4.4.3", @@ -9822,6 +10145,7 @@ "version": "2.2.1", "resolved": "https://registry.npmjs.org/serve-static/-/serve-static-2.2.1.tgz", "integrity": "sha512-xRXBn0pPqQTVQiC8wyQrKs2MOlX24zQ0POGaj0kultvoOCstBQM5yvOhAVSUwOMjQtTvsPWoNCHfPGwaaQJhTw==", + "dev": true, "license": "MIT", "dependencies": { "encodeurl": "^2.0.0", @@ -9848,12 +10172,14 @@ "version": "1.2.0", "resolved": "https://registry.npmjs.org/setprototypeof/-/setprototypeof-1.2.0.tgz", "integrity": "sha512-E5LDX7Wrp85Kil5bhZv46j8jOeboKq5JMmYM3gVGdGH8xFpPWXUMsNrlODCrkoxMEeNi/XZIwuRvY4XNwYMJpw==", + "dev": true, "license": "ISC" }, "node_modules/shebang-command": { "version": "2.0.0", "resolved": "https://registry.npmjs.org/shebang-command/-/shebang-command-2.0.0.tgz", "integrity": "sha512-kHxr2zZpYtdmrN1qDjrrX/Z1rR1kG8Dx+gkpK1G4eXmvXswmcE1hTWBWYUzlraYw1/yZp6YuDY77YtvbN0dmDA==", + "dev": true, "license": "MIT", "dependencies": { "shebang-regex": "^3.0.0" @@ -9866,6 +10192,7 @@ "version": "3.0.0", "resolved": "https://registry.npmjs.org/shebang-regex/-/shebang-regex-3.0.0.tgz", "integrity": "sha512-7++dFhtcx3353uBaq8DDR4NuxBetBzC7ZQOhmTQInHEd6bSrXdiEyzCvG07Z44UYdLShWUyXt5M/yhz8ekcb1A==", + "dev": true, "license": "MIT", "engines": { "node": ">=8" @@ -9875,6 +10202,7 @@ "version": "1.1.0", "resolved": "https://registry.npmjs.org/side-channel/-/side-channel-1.1.0.tgz", "integrity": "sha512-ZX99e6tRweoUXqR+VBrslhda51Nh5MTQwou5tnUDgbtyM0dBgmhEDtWGP/xbKn6hqfPRHujUNwz5fy/wbbhnpw==", + "dev": true, "license": "MIT", "dependencies": { "es-errors": "^1.3.0", @@ -9894,6 +10222,7 @@ "version": "1.0.0", "resolved": "https://registry.npmjs.org/side-channel-list/-/side-channel-list-1.0.0.tgz", "integrity": "sha512-FCLHtRD/gnpCiCHEiJLOwdmFP+wzCmDEkc9y7NsYxeF4u7Btsn1ZuwgwJGxImImHicJArLP4R0yX4c2KCrMrTA==", + "dev": true, "license": "MIT", "dependencies": { "es-errors": "^1.3.0", @@ -9910,6 +10239,7 @@ "version": "1.0.1", "resolved": "https://registry.npmjs.org/side-channel-map/-/side-channel-map-1.0.1.tgz", "integrity": "sha512-VCjCNfgMsby3tTdo02nbjtM/ewra6jPHmpThenkTYh8pG9ucZ/1P8So4u4FGBek/BjpOVsDCMoLA/iuBKIFXRA==", + "dev": true, "license": "MIT", "dependencies": { "call-bound": "^1.0.2", @@ -9928,6 +10258,7 @@ "version": "1.0.2", "resolved": "https://registry.npmjs.org/side-channel-weakmap/-/side-channel-weakmap-1.0.2.tgz", "integrity": "sha512-WPS/HvHQTYnHisLo9McqBHOJk2FkHO/tlpvldyrnem4aeQp4hai3gythswg6p01oSoTl58rcpiFAjF2br2Ak2A==", + "dev": true, "license": "MIT", "dependencies": { "call-bound": "^1.0.2", @@ -9950,23 +10281,10 @@ "dev": true, "license": "ISC" }, - "node_modules/signal-exit": { - "version": "4.1.0", - "resolved": "https://registry.npmjs.org/signal-exit/-/signal-exit-4.1.0.tgz", - "integrity": "sha512-bzyZ1e88w9O1iNJbKnOlvYTrWPDl46O1bG0D3XInv+9tkPrxrN8jUUTiFlDkkmKWgn1M6CfIA13SuGqOa9Korw==", - "dev": true, - "license": "ISC", - "engines": { - "node": ">=14" - }, - "funding": { - "url": "https://github.com/sponsors/isaacs" - } - }, "node_modules/sirv": { - "version": "3.0.1", - "resolved": "https://registry.npmjs.org/sirv/-/sirv-3.0.1.tgz", - "integrity": "sha512-FoqMu0NCGBLCcAkS1qA+XJIQTR6/JHfQXl+uGteNCQ76T91DMUjPa9xfmeqMY3z80nLSg9yQmNjK0Px6RWsH/A==", + "version": "3.0.2", + "resolved": "https://registry.npmjs.org/sirv/-/sirv-3.0.2.tgz", + "integrity": "sha512-2wcC/oGxHis/BoHkkPwldgiPSYcpZK3JU28WoMVv55yHJgcZ8rlXvuG9iZggz+sU1d4bRgIGASwyWqjxu3FM0g==", "dev": true, "license": "MIT", "dependencies": { @@ -10002,6 +10320,7 @@ "version": "2.0.2", "resolved": "https://registry.npmjs.org/space-separated-tokens/-/space-separated-tokens-2.0.2.tgz", "integrity": "sha512-PEGlAwrG8yXGXRjW32fGbg66JAlOAwbObuqVoJpv/mRgoWDQfgH1wDPvtzWyUSNAXBGSk8h755YDbbcEy3SH2Q==", + "dev": true, "license": "MIT", "funding": { "type": "github", @@ -10019,15 +10338,16 @@ "version": "2.0.2", "resolved": "https://registry.npmjs.org/statuses/-/statuses-2.0.2.tgz", "integrity": "sha512-DvEy55V3DB7uknRo+4iOGT5fP1slR8wQohVdknigZPMpMstaKJQWhwiYBACJE3Ul2pTnATihhBYnRhZQHGBiRw==", + "dev": true, "license": "MIT", "engines": { "node": ">= 0.8" } }, "node_modules/std-env": { - "version": "3.9.0", - "resolved": "https://registry.npmjs.org/std-env/-/std-env-3.9.0.tgz", - "integrity": "sha512-UGvjygr6F6tpH7o2qyqR6QYpwraIjKSdtzyBdyytFOHmPZY917kwdwLG0RbOjWOnKmnm3PeHjaoLLMie7kPLQw==", + "version": "4.1.0", + "resolved": "https://registry.npmjs.org/std-env/-/std-env-4.1.0.tgz", + "integrity": "sha512-Rq7ybcX2RuC55r9oaPVEW7/xu3tj8u4GeBYHBWCychFtzMIr86A7e3PPEBPT37sHStKX3+TiX/Fr/ACmJLVlLQ==", "dev": true, "license": "MIT" }, @@ -10067,64 +10387,11 @@ } } }, - "node_modules/string-width": { - "version": "5.1.2", - "resolved": "https://registry.npmjs.org/string-width/-/string-width-5.1.2.tgz", - "integrity": "sha512-HnLOCR3vjcY8beoNLtcjZ5/nxn2afmME6lhrDrebokqMap+XbeW8n9TXpPDOqdGK5qcI3oT0GKTW6wC7EMiVqA==", - "dev": true, - "license": "MIT", - "dependencies": { - "eastasianwidth": "^0.2.0", - "emoji-regex": "^9.2.2", - "strip-ansi": "^7.0.1" - }, - "engines": { - "node": ">=12" - }, - "funding": { - "url": "https://github.com/sponsors/sindresorhus" - } - }, - "node_modules/string-width-cjs": { - "name": "string-width", - "version": "4.2.3", - "resolved": "https://registry.npmjs.org/string-width/-/string-width-4.2.3.tgz", - "integrity": "sha512-wKyQRQpjJ0sIp62ErSZdGsjMJWsap5oRNihHhu6G7JVO/9jIB6UyevL+tXuOqrng8j/cxKTWyWUwvSTriiZz/g==", - "dev": true, - "license": "MIT", - "dependencies": { - "emoji-regex": "^8.0.0", - "is-fullwidth-code-point": "^3.0.0", - "strip-ansi": "^6.0.1" - }, - "engines": { - "node": ">=8" - } - }, - "node_modules/string-width-cjs/node_modules/emoji-regex": { - "version": "8.0.0", - "resolved": "https://registry.npmjs.org/emoji-regex/-/emoji-regex-8.0.0.tgz", - "integrity": "sha512-MSjYzcWNOA0ewAHpz0MxpYFvwg6yjy1NG3xteoqz644VCo/RPgnr1/GGt+ic3iJTzQ8Eu3TdM14SawnVUmGE6A==", - "dev": true, - "license": "MIT" - }, - "node_modules/string-width-cjs/node_modules/strip-ansi": { - "version": "6.0.1", - "resolved": "https://registry.npmjs.org/strip-ansi/-/strip-ansi-6.0.1.tgz", - "integrity": "sha512-Y38VPSHcqkFrCpFnQ9vuSXmquuv5oXOKpGeT6aGrr3o3Gc9AlVa6JBfUSOCnbxGGZF+/0ooI7KrPuUSztUdU5A==", - "dev": true, - "license": "MIT", - "dependencies": { - "ansi-regex": "^5.0.1" - }, - "engines": { - "node": ">=8" - } - }, "node_modules/stringify-entities": { "version": "4.0.4", "resolved": "https://registry.npmjs.org/stringify-entities/-/stringify-entities-4.0.4.tgz", "integrity": "sha512-IwfBptatlO+QCJUo19AqvrPNqlVMpW9YEL2LIVY+Rpv2qsjCGxaDLNRgeGsQWJhfItebuJhsGSLjaBbNSQ+ieg==", + "dev": true, "license": "MIT", "dependencies": { "character-entities-html4": "^2.0.0", @@ -10151,20 +10418,6 @@ "url": "https://github.com/chalk/strip-ansi?sponsor=1" } }, - "node_modules/strip-ansi-cjs": { - "name": "strip-ansi", - "version": "6.0.1", - "resolved": "https://registry.npmjs.org/strip-ansi/-/strip-ansi-6.0.1.tgz", - "integrity": "sha512-Y38VPSHcqkFrCpFnQ9vuSXmquuv5oXOKpGeT6aGrr3o3Gc9AlVa6JBfUSOCnbxGGZF+/0ooI7KrPuUSztUdU5A==", - "dev": true, - "license": "MIT", - "dependencies": { - "ansi-regex": "^5.0.1" - }, - "engines": { - "node": ">=8" - } - }, "node_modules/strip-ansi/node_modules/ansi-regex": { "version": "6.1.0", "resolved": "https://registry.npmjs.org/ansi-regex/-/ansi-regex-6.1.0.tgz", @@ -10204,30 +10457,11 @@ "url": "https://github.com/sponsors/sindresorhus" } }, - "node_modules/strip-literal": { - "version": "3.0.0", - "resolved": "https://registry.npmjs.org/strip-literal/-/strip-literal-3.0.0.tgz", - "integrity": "sha512-TcccoMhJOM3OebGhSBEmp3UZ2SfDMZUEBdRA/9ynfLi8yYajyWX3JiXArcJt4Umh4vISpspkQIY8ZZoCqjbviA==", - "dev": true, - "license": "MIT", - "dependencies": { - "js-tokens": "^9.0.1" - }, - "funding": { - "url": "https://github.com/sponsors/antfu" - } - }, - "node_modules/strip-literal/node_modules/js-tokens": { - "version": "9.0.1", - "resolved": "https://registry.npmjs.org/js-tokens/-/js-tokens-9.0.1.tgz", - "integrity": "sha512-mxa9E9ITFOt0ban3j6L5MpjwegGz6lBQmM1IJkWeBZGcMxto50+eWdjC/52xDbS2vy0k7vIMK0Fe2wfL9OQSpQ==", - "dev": true, - "license": "MIT" - }, "node_modules/style-to-object": { "version": "1.0.9", "resolved": "https://registry.npmjs.org/style-to-object/-/style-to-object-1.0.9.tgz", "integrity": "sha512-G4qppLgKu/k6FwRpHiGiKPaPTFcG3g4wNVX/Qsfu+RqQM30E7Tyu/TEgxcL9PNLF5pdRLwQdE3YKKf+KF2Dzlw==", + "dev": true, "license": "MIT", "dependencies": { "inline-style-parser": "0.2.4" @@ -10237,6 +10471,7 @@ "version": "4.4.0", "resolved": "https://registry.npmjs.org/stylis/-/stylis-4.4.0.tgz", "integrity": "sha512-5Z9ZpRzfuH6l/UAvCPAPUo3665Nk2wLaZU3x+TLHKVzIz33+sbJqbtrYoC3KD4/uVOr2Zp+L0LySezP9OHV9yA==", + "dev": true, "license": "MIT" }, "node_modules/supports-color": { @@ -10256,6 +10491,7 @@ "version": "5.55.7", "resolved": "https://registry.npmjs.org/svelte/-/svelte-5.55.7.tgz", "integrity": "sha512-ymI5ykLPwIHW839E053FQbI1G+jnRFJEw3Kv5Y4njixVWywQBx+NUFpkkKyk5LIb36Fg9DVXSYpqiGekLD0hyw==", + "dev": true, "license": "MIT", "dependencies": { "@jridgewell/remapping": "^2.3.4", @@ -10389,6 +10625,7 @@ "version": "1.0.5", "resolved": "https://registry.npmjs.org/svelte-sonner/-/svelte-sonner-1.0.5.tgz", "integrity": "sha512-9dpGPFqKb/QWudYqGnEz93vuY+NgCEvyNvxoCLMVGw6sDN/3oVeKV1xiEirW2E1N3vJEyj5imSBNOGltQHA7mg==", + "dev": true, "license": "MIT", "dependencies": { "runed": "^0.28.0" @@ -10401,6 +10638,7 @@ "version": "0.28.0", "resolved": "https://registry.npmjs.org/runed/-/runed-0.28.0.tgz", "integrity": "sha512-k2xx7RuO9hWcdd9f+8JoBeqWtYrm5CALfgpkg2YDB80ds/QE4w0qqu34A7fqiAwiBBSBQOid7TLxwxVC27ymWQ==", + "dev": true, "funding": [ "https://github.com/sponsors/huntabyte", "https://github.com/sponsors/tglide" @@ -10417,6 +10655,7 @@ "version": "0.7.1", "resolved": "https://registry.npmjs.org/svelte-toolbelt/-/svelte-toolbelt-0.7.1.tgz", "integrity": "sha512-HcBOcR17Vx9bjaOceUvxkY3nGmbBmCBBbuWLLEWO6jtmWH8f/QoWmbyUfQZrpDINH39en1b8mptfPQT9VKQ1xQ==", + "dev": true, "funding": [ "https://github.com/sponsors/huntabyte" ], @@ -10437,6 +10676,7 @@ "version": "0.23.4", "resolved": "https://registry.npmjs.org/runed/-/runed-0.23.4.tgz", "integrity": "sha512-9q8oUiBYeXIDLWNK5DfCWlkL0EW3oGbk845VdKlPeia28l751VpfesaB/+7pI6rnbx1I6rqoZ2fZxptOJLxILA==", + "dev": true, "funding": [ "https://github.com/sponsors/huntabyte", "https://github.com/sponsors/tglide" @@ -10452,6 +10692,7 @@ "version": "5.3.1", "resolved": "https://registry.npmjs.org/aria-query/-/aria-query-5.3.1.tgz", "integrity": "sha512-Z/ZeOgVl7bcSYZ/u/rh0fOpvEpq//LZmdbkXyc7syVzjPAhfOa9ebsdTSjEBDU4vs5nC98Kfduj1uFo0qyET3g==", + "dev": true, "license": "Apache-2.0", "engines": { "node": ">= 0.4" @@ -10461,6 +10702,7 @@ "version": "2.2.4", "resolved": "https://registry.npmjs.org/esrap/-/esrap-2.2.4.tgz", "integrity": "sha512-suICpxAmZ9A8bzJjEl/+rLJiDKC0X4gYWUxT6URAWBLvlXmtbZd5ySMu/N2ZGEtMCAmflUDPSehrP9BQcsGcSg==", + "dev": true, "license": "MIT", "dependencies": { "@jridgewell/sourcemap-codec": "^1.4.15", @@ -10471,6 +10713,7 @@ "version": "3.0.3", "resolved": "https://registry.npmjs.org/is-reference/-/is-reference-3.0.3.tgz", "integrity": "sha512-ixkJoqQvAP88E6wLydLGGqCJsrFUnqoH6HnaczB8XmDH1oaWU+xxdptvikTgaEhtZ53Ky6YXiBuUI2WXLMCwjw==", + "dev": true, "license": "MIT", "dependencies": { "@types/estree": "^1.0.6" @@ -10563,47 +10806,6 @@ "node": ">=18" } }, - "node_modules/test-exclude": { - "version": "7.0.1", - "resolved": "https://registry.npmjs.org/test-exclude/-/test-exclude-7.0.1.tgz", - "integrity": "sha512-pFYqmTw68LXVjeWJMST4+borgQP2AyMNbg1BpZh9LbyhUeNkeaPF9gzfPGUAnSMV3qPYdWUwDIjjCLiSDOl7vg==", - "dev": true, - "license": "ISC", - "dependencies": { - "@istanbuljs/schema": "^0.1.2", - "glob": "^10.4.1", - "minimatch": "^9.0.4" - }, - "engines": { - "node": ">=18" - } - }, - "node_modules/test-exclude/node_modules/brace-expansion": { - "version": "2.0.3", - "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-2.0.3.tgz", - "integrity": "sha512-MCV/fYJEbqx68aE58kv2cA/kiky1G8vux3OR6/jbS+jIMe/6fJWa0DTzJU7dqijOWYwHi1t29FlfYI9uytqlpA==", - "dev": true, - "license": "MIT", - "dependencies": { - "balanced-match": "^1.0.0" - } - }, - "node_modules/test-exclude/node_modules/minimatch": { - "version": "9.0.9", - "resolved": "https://registry.npmjs.org/minimatch/-/minimatch-9.0.9.tgz", - "integrity": "sha512-OBwBN9AL4dqmETlpS2zasx+vTeWclWzkblfZk7KTA5j3jeOONz/tRCnZomUyvNg83wL5Zv9Ss6HMJXAgL8R2Yg==", - "dev": true, - "license": "ISC", - "dependencies": { - "brace-expansion": "^2.0.2" - }, - "engines": { - "node": ">=16 || 14 >=14.17" - }, - "funding": { - "url": "https://github.com/sponsors/isaacs" - } - }, "node_modules/tiny-invariant": { "version": "1.3.3", "resolved": "https://registry.npmjs.org/tiny-invariant/-/tiny-invariant-1.3.3.tgz", @@ -10619,11 +10821,14 @@ "license": "MIT" }, "node_modules/tinyexec": { - "version": "0.3.2", - "resolved": "https://registry.npmjs.org/tinyexec/-/tinyexec-0.3.2.tgz", - "integrity": "sha512-KQQR9yN7R5+OSwaK0XQoj22pwHoTlgYqmUscPYoknOoWCWfj/5/ABTMRi69FrKU5ffPVh5QcFikpWJI/P1ocHA==", + "version": "1.2.4", + "resolved": "https://registry.npmjs.org/tinyexec/-/tinyexec-1.2.4.tgz", + "integrity": "sha512-SHf/r48b7vOrjve9PxJo3MN5v5yuyjHvdUcrQffT3WXMUfnGmHDVbC4k3sHJaJTgZCwpUplIaAo5ANtMyp3YHg==", "dev": true, - "license": "MIT" + "license": "MIT", + "engines": { + "node": ">=18" + } }, "node_modules/tinyglobby": { "version": "0.2.15", @@ -10642,16 +10847,6 @@ "url": "https://github.com/sponsors/SuperchupuDev" } }, - "node_modules/tinypool": { - "version": "1.1.1", - "resolved": "https://registry.npmjs.org/tinypool/-/tinypool-1.1.1.tgz", - "integrity": "sha512-Zba82s87IFq9A9XmjiX5uZA/ARWDrB03OHlq+Vw1fSdt0I+4/Kutwy8BP4Y/y/aORMo61FQ0vIb5j44vSo5Pkg==", - "dev": true, - "license": "MIT", - "engines": { - "node": "^18.0.0 || >=20.0.0" - } - }, "node_modules/tinyrainbow": { "version": "2.0.0", "resolved": "https://registry.npmjs.org/tinyrainbow/-/tinyrainbow-2.0.0.tgz", @@ -10690,6 +10885,7 @@ "version": "1.0.1", "resolved": "https://registry.npmjs.org/toidentifier/-/toidentifier-1.0.1.tgz", "integrity": "sha512-o5sSPKEkg/DIQNmH43V0/uerLrpzVedkUh8tGNvaeXpfpuwjKenlSox/2O/BTlZUtEe+JG7s5YhEz608PlAHRA==", + "dev": true, "license": "MIT", "engines": { "node": ">=0.6" @@ -10709,6 +10905,7 @@ "version": "3.0.1", "resolved": "https://registry.npmjs.org/trim-lines/-/trim-lines-3.0.1.tgz", "integrity": "sha512-kRj8B+YHZCc9kQYdWfJB2/oUl9rA99qbowYYBtr4ui4mZyAQ2JpvVBd/6U2YloATfqBhBTSMhTpgBHtU0Mf3Rg==", + "dev": true, "license": "MIT", "funding": { "type": "github", @@ -10719,6 +10916,7 @@ "version": "2.2.0", "resolved": "https://registry.npmjs.org/trough/-/trough-2.2.0.tgz", "integrity": "sha512-tmMpK00BjZiUyVyvrBK7knerNgmgvcV/KLVyuma/SC+TQN167GrMRciANTz09+k3zW8L8t60jWO1GpfkZdjTaw==", + "dev": true, "license": "MIT", "funding": { "type": "github", @@ -10742,6 +10940,7 @@ "version": "2.2.0", "resolved": "https://registry.npmjs.org/ts-dedent/-/ts-dedent-2.2.0.tgz", "integrity": "sha512-q5W7tVM71e2xjHZTlgfTDoPF/SmqKG5hddq9SzR49CH2hayqRKJtQ4mtRlSxKaJlR/+9rEM+mnBHf7I2/BQcpQ==", + "dev": true, "license": "MIT", "engines": { "node": ">=6.10" @@ -10794,6 +10993,7 @@ "version": "2.0.1", "resolved": "https://registry.npmjs.org/type-is/-/type-is-2.0.1.tgz", "integrity": "sha512-OZs6gsjF4vMp32qrCbiVSkrFmXtG/AZhY3t0iAMrMBiAZyV9oALtXO8hsrHbMXF9x6L3grlFuwW2oAz7cav+Gw==", + "dev": true, "license": "MIT", "dependencies": { "content-type": "^1.0.5", @@ -10853,6 +11053,7 @@ "version": "11.0.5", "resolved": "https://registry.npmjs.org/unified/-/unified-11.0.5.tgz", "integrity": "sha512-xKvGhPWw3k84Qjh8bI3ZeJjqnyadK+GEFtazSfZv/rKeTkTjOJho6mFqh2SM96iIcZokxiOpg78GazTSg8+KHA==", + "dev": true, "license": "MIT", "dependencies": { "@types/unist": "^3.0.0", @@ -10872,6 +11073,7 @@ "version": "3.0.3", "resolved": "https://registry.npmjs.org/@types/unist/-/unist-3.0.3.tgz", "integrity": "sha512-ko/gIFJRv177XgZsZcBwnqJN5x/Gien8qNOn0D5bQU/zAzVf9Zt3BlcUiLqhV9y4ARk0GbT3tnUiPNgnTXzc/Q==", + "dev": true, "license": "MIT" }, "node_modules/union": { @@ -10890,6 +11092,7 @@ "version": "5.0.0", "resolved": "https://registry.npmjs.org/unist-util-find-after/-/unist-util-find-after-5.0.0.tgz", "integrity": "sha512-amQa0Ep2m6hE2g72AugUItjbuM8X8cGQnFoHk0pGfrFeT9GZhzN5SW8nRsiGKK7Aif4CrACPENkA6P/Lw6fHGQ==", + "dev": true, "license": "MIT", "dependencies": { "@types/unist": "^3.0.0", @@ -10904,12 +11107,14 @@ "version": "3.0.3", "resolved": "https://registry.npmjs.org/@types/unist/-/unist-3.0.3.tgz", "integrity": "sha512-ko/gIFJRv177XgZsZcBwnqJN5x/Gien8qNOn0D5bQU/zAzVf9Zt3BlcUiLqhV9y4ARk0GbT3tnUiPNgnTXzc/Q==", + "dev": true, "license": "MIT" }, "node_modules/unist-util-is": { "version": "6.0.0", "resolved": "https://registry.npmjs.org/unist-util-is/-/unist-util-is-6.0.0.tgz", "integrity": "sha512-2qCTHimwdxLfz+YzdGfkqNlH0tLi9xjTnHddPmJwtIG9MGsdbutfTc4P+haPD7l7Cjxf/WZj+we5qfVPvvxfYw==", + "dev": true, "license": "MIT", "dependencies": { "@types/unist": "^3.0.0" @@ -10923,12 +11128,14 @@ "version": "3.0.3", "resolved": "https://registry.npmjs.org/@types/unist/-/unist-3.0.3.tgz", "integrity": "sha512-ko/gIFJRv177XgZsZcBwnqJN5x/Gien8qNOn0D5bQU/zAzVf9Zt3BlcUiLqhV9y4ARk0GbT3tnUiPNgnTXzc/Q==", + "dev": true, "license": "MIT" }, "node_modules/unist-util-position": { "version": "5.0.0", "resolved": "https://registry.npmjs.org/unist-util-position/-/unist-util-position-5.0.0.tgz", "integrity": "sha512-fucsC7HjXvkB5R3kTCO7kUjRdrS0BJt3M/FPxmHMBOm8JQi2BsHAHFsy27E0EolP8rp0NzXsJ+jNPyDWvOJZPA==", + "dev": true, "license": "MIT", "dependencies": { "@types/unist": "^3.0.0" @@ -10942,6 +11149,7 @@ "version": "3.0.3", "resolved": "https://registry.npmjs.org/@types/unist/-/unist-3.0.3.tgz", "integrity": "sha512-ko/gIFJRv177XgZsZcBwnqJN5x/Gien8qNOn0D5bQU/zAzVf9Zt3BlcUiLqhV9y4ARk0GbT3tnUiPNgnTXzc/Q==", + "dev": true, "license": "MIT" }, "node_modules/unist-util-remove-position": { @@ -10984,6 +11192,7 @@ "version": "5.0.0", "resolved": "https://registry.npmjs.org/unist-util-visit/-/unist-util-visit-5.0.0.tgz", "integrity": "sha512-MR04uvD+07cwl/yhVuVWAtw+3GOR/knlL55Nd/wAdblk27GCVt3lqpTivy/tkJcZoNPzTwS1Y+KMojlLDhoTzg==", + "dev": true, "license": "MIT", "dependencies": { "@types/unist": "^3.0.0", @@ -10999,6 +11208,7 @@ "version": "6.0.1", "resolved": "https://registry.npmjs.org/unist-util-visit-parents/-/unist-util-visit-parents-6.0.1.tgz", "integrity": "sha512-L/PqWzfTP9lzzEa6CKs0k2nARxTdZduw3zyh8d2NVBnsyvHjSX4TWse388YrrQKbvI8w20fGjGlhgT96WwKykw==", + "dev": true, "license": "MIT", "dependencies": { "@types/unist": "^3.0.0", @@ -11013,12 +11223,14 @@ "version": "3.0.3", "resolved": "https://registry.npmjs.org/@types/unist/-/unist-3.0.3.tgz", "integrity": "sha512-ko/gIFJRv177XgZsZcBwnqJN5x/Gien8qNOn0D5bQU/zAzVf9Zt3BlcUiLqhV9y4ARk0GbT3tnUiPNgnTXzc/Q==", + "dev": true, "license": "MIT" }, "node_modules/unist-util-visit/node_modules/@types/unist": { "version": "3.0.3", "resolved": "https://registry.npmjs.org/@types/unist/-/unist-3.0.3.tgz", "integrity": "sha512-ko/gIFJRv177XgZsZcBwnqJN5x/Gien8qNOn0D5bQU/zAzVf9Zt3BlcUiLqhV9y4ARk0GbT3tnUiPNgnTXzc/Q==", + "dev": true, "license": "MIT" }, "node_modules/universalify": { @@ -11035,6 +11247,7 @@ "version": "1.0.0", "resolved": "https://registry.npmjs.org/unpipe/-/unpipe-1.0.0.tgz", "integrity": "sha512-pjy2bYhSsufwWlKwPc+l3cN7+wuJlK6uz0YdJEOlQDbl6jo/YlPi4mb8agUkVC8BF7V8NuzeyPNqRksA3hztKQ==", + "dev": true, "license": "MIT", "engines": { "node": ">= 0.8" @@ -11094,6 +11307,7 @@ "version": "13.0.2", "resolved": "https://registry.npmjs.org/uuid/-/uuid-13.0.2.tgz", "integrity": "sha512-vzi9uRZ926x4XV73S/4qQaTwPXM2JBj6/6lI/byHH1jOpCzb0zDbfytgA9LcN/hzb2l7WQSQnxITOVx5un/wGw==", + "dev": true, "funding": [ "https://github.com/sponsors/broofa", "https://github.com/sponsors/ctavan" @@ -11107,6 +11321,7 @@ "version": "1.1.2", "resolved": "https://registry.npmjs.org/vary/-/vary-1.1.2.tgz", "integrity": "sha512-BNGbWLfd0eUPabhkXUVm0j8uuvREyTh5ovRa/dyow/BqAbZJyC+5fU+IzQOzmAKzYqYRAISoRhdQr3eIZ/PXqg==", + "dev": true, "license": "MIT", "engines": { "node": ">= 0.8" @@ -11116,6 +11331,7 @@ "version": "6.0.3", "resolved": "https://registry.npmjs.org/vfile/-/vfile-6.0.3.tgz", "integrity": "sha512-KzIbH/9tXat2u30jf+smMwFCsno4wHVdNmzFyL+T/L3UGqqk6JKfVqOFOZEpZSHADH1k40ab6NUIXZq422ov3Q==", + "dev": true, "license": "MIT", "dependencies": { "@types/unist": "^3.0.0", @@ -11167,12 +11383,14 @@ "version": "3.0.3", "resolved": "https://registry.npmjs.org/@types/unist/-/unist-3.0.3.tgz", "integrity": "sha512-ko/gIFJRv177XgZsZcBwnqJN5x/Gien8qNOn0D5bQU/zAzVf9Zt3BlcUiLqhV9y4ARk0GbT3tnUiPNgnTXzc/Q==", + "dev": true, "license": "MIT" }, "node_modules/vfile/node_modules/unist-util-stringify-position": { "version": "4.0.0", "resolved": "https://registry.npmjs.org/unist-util-stringify-position/-/unist-util-stringify-position-4.0.0.tgz", "integrity": "sha512-0ASV06AAoKCDkS2+xw5RXJywruurpbC4JZSm7nr7MOt1ojAzvyyaO+UxZf18j8FCF6kmzCZKcAgN/yu2gm2XgQ==", + "dev": true, "license": "MIT", "dependencies": { "@types/unist": "^3.0.0" @@ -11186,6 +11404,7 @@ "version": "4.0.2", "resolved": "https://registry.npmjs.org/vfile-message/-/vfile-message-4.0.2.tgz", "integrity": "sha512-jRDZ1IMLttGj41KcZvlrYAaI3CfqpLpfpf+Mfig13viT6NKvRzWZ+lXz0Y5D60w6uJIBAOGq9mSHf0gktF0duw==", + "dev": true, "license": "MIT", "dependencies": { "@types/unist": "^3.0.0", @@ -11271,29 +11490,6 @@ } } }, - "node_modules/vite-node": { - "version": "3.2.4", - "resolved": "https://registry.npmjs.org/vite-node/-/vite-node-3.2.4.tgz", - "integrity": "sha512-EbKSKh+bh1E1IFxeO0pg1n4dvoOTt0UDiXMd/qn++r98+jPO1xtJilvXldeuQ8giIB5IkpjCgMleHMNEsGH6pg==", - "dev": true, - "license": "MIT", - "dependencies": { - "cac": "^6.7.14", - "debug": "^4.4.1", - "es-module-lexer": "^1.7.0", - "pathe": "^2.0.3", - "vite": "^5.0.0 || ^6.0.0 || ^7.0.0-0" - }, - "bin": { - "vite-node": "vite-node.mjs" - }, - "engines": { - "node": "^18.0.0 || ^20.0.0 || >=22.0.0" - }, - "funding": { - "url": "https://opencollective.com/vitest" - } - }, "node_modules/vite-plugin-devtools-json": { "version": "0.2.1", "resolved": "https://registry.npmjs.org/vite-plugin-devtools-json/-/vite-plugin-devtools-json-0.2.1.tgz", @@ -11357,65 +11553,79 @@ } }, "node_modules/vitest": { - "version": "3.2.4", - "resolved": "https://registry.npmjs.org/vitest/-/vitest-3.2.4.tgz", - "integrity": "sha512-LUCP5ev3GURDysTWiP47wRRUpLKMOfPh+yKTx3kVIEiu5KOMeqzpnYNsKyOoVrULivR8tLcks4+lga33Whn90A==", - "dev": true, - "license": "MIT", - "dependencies": { - "@types/chai": "^5.2.2", - "@vitest/expect": "3.2.4", - "@vitest/mocker": "3.2.4", - "@vitest/pretty-format": "^3.2.4", - "@vitest/runner": "3.2.4", - "@vitest/snapshot": "3.2.4", - "@vitest/spy": "3.2.4", - "@vitest/utils": "3.2.4", - "chai": "^5.2.0", - "debug": "^4.4.1", - "expect-type": "^1.2.1", - "magic-string": "^0.30.17", + "version": "4.1.8", + "resolved": "https://registry.npmjs.org/vitest/-/vitest-4.1.8.tgz", + "integrity": "sha512-flY6ScbCIt9HThs+C5HS7jvGOB560DJtk/Z15IQROTA6zEy49Nh8T/dofWTQL+n3vswqn87sbJNiuqw1SDp5Ig==", + "dev": true, + "license": "MIT", + "dependencies": { + "@vitest/expect": "4.1.8", + "@vitest/mocker": "4.1.8", + "@vitest/pretty-format": "4.1.8", + "@vitest/runner": "4.1.8", + "@vitest/snapshot": "4.1.8", + "@vitest/spy": "4.1.8", + "@vitest/utils": "4.1.8", + "es-module-lexer": "^2.0.0", + "expect-type": "^1.3.0", + "magic-string": "^0.30.21", + "obug": "^2.1.1", "pathe": "^2.0.3", - "picomatch": "^4.0.2", - "std-env": "^3.9.0", + "picomatch": "^4.0.3", + "std-env": "^4.0.0-rc.1", "tinybench": "^2.9.0", - "tinyexec": "^0.3.2", - "tinyglobby": "^0.2.14", - "tinypool": "^1.1.1", - "tinyrainbow": "^2.0.0", - "vite": "^5.0.0 || ^6.0.0 || ^7.0.0-0", - "vite-node": "3.2.4", + "tinyexec": "^1.0.2", + "tinyglobby": "^0.2.15", + "tinyrainbow": "^3.1.0", + "vite": "^6.0.0 || ^7.0.0 || ^8.0.0", "why-is-node-running": "^2.3.0" }, "bin": { "vitest": "vitest.mjs" }, "engines": { - "node": "^18.0.0 || ^20.0.0 || >=22.0.0" + "node": "^20.0.0 || ^22.0.0 || >=24.0.0" }, "funding": { "url": "https://opencollective.com/vitest" }, "peerDependencies": { "@edge-runtime/vm": "*", - "@types/debug": "^4.1.12", - "@types/node": "^18.0.0 || ^20.0.0 || >=22.0.0", - "@vitest/browser": "3.2.4", - "@vitest/ui": "3.2.4", + "@opentelemetry/api": "^1.9.0", + "@types/node": "^20.0.0 || ^22.0.0 || >=24.0.0", + "@vitest/browser-playwright": "4.1.8", + "@vitest/browser-preview": "4.1.8", + "@vitest/browser-webdriverio": "4.1.8", + "@vitest/coverage-istanbul": "4.1.8", + "@vitest/coverage-v8": "4.1.8", + "@vitest/ui": "4.1.8", "happy-dom": "*", - "jsdom": "*" + "jsdom": "*", + "vite": "^6.0.0 || ^7.0.0 || ^8.0.0" }, "peerDependenciesMeta": { "@edge-runtime/vm": { "optional": true }, - "@types/debug": { + "@opentelemetry/api": { "optional": true }, "@types/node": { "optional": true }, - "@vitest/browser": { + "@vitest/browser-playwright": { + "optional": true + }, + "@vitest/browser-preview": { + "optional": true + }, + "@vitest/browser-webdriverio": { + "optional": true + }, + "@vitest/coverage-istanbul": { + "optional": true + }, + "@vitest/coverage-v8": { "optional": true }, "@vitest/ui": { @@ -11426,25 +11636,103 @@ }, "jsdom": { "optional": true + }, + "vite": { + "optional": false } } }, "node_modules/vitest-browser-svelte": { - "version": "0.1.0", - "resolved": "https://registry.npmjs.org/vitest-browser-svelte/-/vitest-browser-svelte-0.1.0.tgz", - "integrity": "sha512-YB6ZUZZQNqU1T9NzvTEDpwpPv35Ng1NZMPBh81zDrLEdOgROGE6nJb79NWb1Eu/a8VkHifqArpOZfJfALge6xQ==", + "version": "2.1.1", + "resolved": "https://registry.npmjs.org/vitest-browser-svelte/-/vitest-browser-svelte-2.1.1.tgz", + "integrity": "sha512-qbunYRSm+N92r9bfTkdDTpBZESLmp4QFz2SluV3n/x8U7ysosfeXYJZ4vXbJ0Y0LzoqqDnV5LHprmFgn4Eo+Ug==", "dev": true, "license": "MIT", - "engines": { - "node": "^18.0.0 || >=20.0.0" + "dependencies": { + "@testing-library/svelte-core": "^1.0.0" }, "funding": { "url": "https://opencollective.com/vitest" }, "peerDependencies": { - "@vitest/browser": "^2.1.0 || ^3.0.0-0", - "svelte": ">3.0.0", - "vitest": "^2.1.0 || ^3.0.0-0" + "svelte": "^3 || ^4 || ^5 || ^5.0.0-next.0", + "vitest": "^4.0.0" + } + }, + "node_modules/vitest/node_modules/@vitest/expect": { + "version": "4.1.8", + "resolved": "https://registry.npmjs.org/@vitest/expect/-/expect-4.1.8.tgz", + "integrity": "sha512-h3nDO677RDLEGlBxyQ5CW8RlMThSKSRLUePLOx09gNIWRL40edgA1GCZSZgf1W55MFAG6/Sw14KeaAnqv0NKdQ==", + "dev": true, + "license": "MIT", + "dependencies": { + "@standard-schema/spec": "^1.1.0", + "@types/chai": "^5.2.2", + "@vitest/spy": "4.1.8", + "@vitest/utils": "4.1.8", + "chai": "^6.2.2", + "tinyrainbow": "^3.1.0" + }, + "funding": { + "url": "https://opencollective.com/vitest" + } + }, + "node_modules/vitest/node_modules/@vitest/pretty-format": { + "version": "4.1.8", + "resolved": "https://registry.npmjs.org/@vitest/pretty-format/-/pretty-format-4.1.8.tgz", + "integrity": "sha512-9GasEBxpZ1VYIpqHf/0+YGg121uSNwCKOJqIrTwWP/TB7DmFCiaBpNl3aPZzoLWfWkuqhbH8vJIVobZkvdo2cA==", + "dev": true, + "license": "MIT", + "dependencies": { + "tinyrainbow": "^3.1.0" + }, + "funding": { + "url": "https://opencollective.com/vitest" + } + }, + "node_modules/vitest/node_modules/@vitest/spy": { + "version": "4.1.8", + "resolved": "https://registry.npmjs.org/@vitest/spy/-/spy-4.1.8.tgz", + "integrity": "sha512-6EevtBp6OZOPF7bmz36HrGMeP3txgVSrgebWxHOafDXGkhIzfXK14f8KF6MuFfgXXUeHxmpD3BQxkV00/3s5mA==", + "dev": true, + "license": "MIT", + "funding": { + "url": "https://opencollective.com/vitest" + } + }, + "node_modules/vitest/node_modules/@vitest/utils": { + "version": "4.1.8", + "resolved": "https://registry.npmjs.org/@vitest/utils/-/utils-4.1.8.tgz", + "integrity": "sha512-uOJamYALNhfJ6iolExyQM40yIQwDqYnkKtQ5VCiSe17E33H0aQ/u+1GlRuz4LZBk6Mm3sg90G9hEbmEt37C1Zg==", + "dev": true, + "license": "MIT", + "dependencies": { + "@vitest/pretty-format": "4.1.8", + "convert-source-map": "^2.0.0", + "tinyrainbow": "^3.1.0" + }, + "funding": { + "url": "https://opencollective.com/vitest" + } + }, + "node_modules/vitest/node_modules/chai": { + "version": "6.2.2", + "resolved": "https://registry.npmjs.org/chai/-/chai-6.2.2.tgz", + "integrity": "sha512-NUPRluOfOiTKBKvWPtSD4PhFvWCqOi0BGStNWs57X9js7XGTprSmFoz5F0tWhR4WPjNeR9jXqdC7/UpSJTnlRg==", + "dev": true, + "license": "MIT", + "engines": { + "node": ">=18" + } + }, + "node_modules/vitest/node_modules/tinyrainbow": { + "version": "3.1.0", + "resolved": "https://registry.npmjs.org/tinyrainbow/-/tinyrainbow-3.1.0.tgz", + "integrity": "sha512-Bf+ILmBgretUrdJxzXM0SgXLZ3XfiaUuOj/IKQHuTXip+05Xn+uyEYdVg0kYDipTBcLrCVyUzAPz7QmArb0mmw==", + "dev": true, + "license": "MIT", + "engines": { + "node": ">=14.0.0" } }, "node_modules/web-namespaces": { @@ -11482,6 +11770,7 @@ "version": "2.0.2", "resolved": "https://registry.npmjs.org/which/-/which-2.0.2.tgz", "integrity": "sha512-BLI3Tl1TW3Pvl70l3yq3Y64i+awpwXqsGBYWkkqMtnbXgrMD+yj7rhW0kuEDxzJaYXGjEW5ogapKNMEKNMjibA==", + "dev": true, "license": "ISC", "dependencies": { "isexe": "^2.0.0" @@ -11520,95 +11809,11 @@ "node": ">=0.10.0" } }, - "node_modules/wrap-ansi": { - "version": "8.1.0", - "resolved": "https://registry.npmjs.org/wrap-ansi/-/wrap-ansi-8.1.0.tgz", - "integrity": "sha512-si7QWI6zUMq56bESFvagtmzMdGOtoxfR+Sez11Mobfc7tm+VkUckk9bW2UeffTGVUbOksxmSw0AA2gs8g71NCQ==", - "dev": true, - "license": "MIT", - "dependencies": { - "ansi-styles": "^6.1.0", - "string-width": "^5.0.1", - "strip-ansi": "^7.0.1" - }, - "engines": { - "node": ">=12" - }, - "funding": { - "url": "https://github.com/chalk/wrap-ansi?sponsor=1" - } - }, - "node_modules/wrap-ansi-cjs": { - "name": "wrap-ansi", - "version": "7.0.0", - "resolved": "https://registry.npmjs.org/wrap-ansi/-/wrap-ansi-7.0.0.tgz", - "integrity": "sha512-YVGIj2kamLSTxw6NsZjoBxfSwsn0ycdesmc4p+Q21c5zPuZ1pl+NfxVdxPtdHvmNVOQ6XSYG4AUtyt/Fi7D16Q==", - "dev": true, - "license": "MIT", - "dependencies": { - "ansi-styles": "^4.0.0", - "string-width": "^4.1.0", - "strip-ansi": "^6.0.0" - }, - "engines": { - "node": ">=10" - }, - "funding": { - "url": "https://github.com/chalk/wrap-ansi?sponsor=1" - } - }, - "node_modules/wrap-ansi-cjs/node_modules/emoji-regex": { - "version": "8.0.0", - "resolved": "https://registry.npmjs.org/emoji-regex/-/emoji-regex-8.0.0.tgz", - "integrity": "sha512-MSjYzcWNOA0ewAHpz0MxpYFvwg6yjy1NG3xteoqz644VCo/RPgnr1/GGt+ic3iJTzQ8Eu3TdM14SawnVUmGE6A==", - "dev": true, - "license": "MIT" - }, - "node_modules/wrap-ansi-cjs/node_modules/string-width": { - "version": "4.2.3", - "resolved": "https://registry.npmjs.org/string-width/-/string-width-4.2.3.tgz", - "integrity": "sha512-wKyQRQpjJ0sIp62ErSZdGsjMJWsap5oRNihHhu6G7JVO/9jIB6UyevL+tXuOqrng8j/cxKTWyWUwvSTriiZz/g==", - "dev": true, - "license": "MIT", - "dependencies": { - "emoji-regex": "^8.0.0", - "is-fullwidth-code-point": "^3.0.0", - "strip-ansi": "^6.0.1" - }, - "engines": { - "node": ">=8" - } - }, - "node_modules/wrap-ansi-cjs/node_modules/strip-ansi": { - "version": "6.0.1", - "resolved": "https://registry.npmjs.org/strip-ansi/-/strip-ansi-6.0.1.tgz", - "integrity": "sha512-Y38VPSHcqkFrCpFnQ9vuSXmquuv5oXOKpGeT6aGrr3o3Gc9AlVa6JBfUSOCnbxGGZF+/0ooI7KrPuUSztUdU5A==", - "dev": true, - "license": "MIT", - "dependencies": { - "ansi-regex": "^5.0.1" - }, - "engines": { - "node": ">=8" - } - }, - "node_modules/wrap-ansi/node_modules/ansi-styles": { - "version": "6.2.3", - "resolved": "https://registry.npmjs.org/ansi-styles/-/ansi-styles-6.2.3.tgz", - "integrity": "sha512-4Dj6M28JB+oAH8kFkTLUo+a2jwOFkuqb3yucU0CANcRRUbxS0cP0nZYCGjcc3BNXwRIsUVmDGgzawme7zvJHvg==", - "dev": true, - "license": "MIT", - "engines": { - "node": ">=12" - }, - "funding": { - "url": "https://github.com/chalk/ansi-styles?sponsor=1" - } - }, "node_modules/wrappy": { "version": "1.0.2", "resolved": "https://registry.npmjs.org/wrappy/-/wrappy-1.0.2.tgz", "integrity": "sha512-l4Sp/DRseor9wL6EvV2+TuQn63dMkPjZ/sp9XkghTEbV9KlPS1xUsZ3u7/IQO4wxtcFB4bgpQPRcR3QCvezPcQ==", + "dev": true, "license": "ISC" }, "node_modules/ws": { @@ -11676,12 +11881,14 @@ "version": "1.1.2", "resolved": "https://registry.npmjs.org/zimmerframe/-/zimmerframe-1.1.2.tgz", "integrity": "sha512-rAbqEGa8ovJy4pyBxZM70hg4pE6gDgaQ0Sl9M3enG3I0d6H4XSAM3GeNGLKnsBpuijUow064sf7ww1nutC5/3w==", + "dev": true, "license": "MIT" }, "node_modules/zod": { "version": "4.2.1", "resolved": "https://registry.npmjs.org/zod/-/zod-4.2.1.tgz", "integrity": "sha512-0wZ1IRqGGhMP76gLqz8EyfBXKk0J2qo2+H3fi4mcUP/KtTocoX08nmIAHl1Z2kJIZbZee8KOpBCSNPRgauucjw==", + "dev": true, "license": "MIT", "funding": { "url": "https://github.com/sponsors/colinhacks" @@ -11691,6 +11898,7 @@ "version": "3.25.1", "resolved": "https://registry.npmjs.org/zod-to-json-schema/-/zod-to-json-schema-3.25.1.tgz", "integrity": "sha512-pM/SU9d3YAggzi6MtR4h7ruuQlqKtad8e9S0fmxcMi+ueAK5Korys/aWcV9LIIHTVbj01NdzxcnXSN+O74ZIVA==", + "dev": true, "license": "ISC", "peerDependencies": { "zod": "^3.25 || ^4" @@ -11700,6 +11908,7 @@ "version": "2.0.4", "resolved": "https://registry.npmjs.org/zwitch/-/zwitch-2.0.4.tgz", "integrity": "sha512-bXE4cR/kVZhKZX/RjPEflHaKVhUVl85noU3v6b8apfQEc1x4A+zBxjZ4lN8LqGd6WZ3dl98pY4o717VFmoPp+A==", + "dev": true, "license": "MIT", "funding": { "type": "github", diff --git a/tools/ui/package.json b/tools/ui/package.json index 7c514fa8a6a0..4f5ef4d64fa0 100644 --- a/tools/ui/package.json +++ b/tools/ui/package.json @@ -23,75 +23,77 @@ "cleanup": "rm -rf .svelte-kit build node_modules test-results" }, "devDependencies": { - "@chromatic-com/storybook": "^5.0.0", - "@eslint/compat": "^1.2.5", - "@eslint/js": "^9.18.0", - "@internationalized/date": "^3.10.1", - "@lucide/svelte": "^0.515.0", - "@playwright/test": "^1.49.1", - "@storybook/addon-a11y": "^10.2.4", - "@storybook/addon-docs": "^10.2.4", - "@storybook/addon-svelte-csf": "^5.0.10", - "@storybook/addon-vitest": "^10.2.4", - "@storybook/sveltekit": "^10.2.4", - "@sveltejs/adapter-static": "^3.0.10", - "@sveltejs/kit": "^2.48.4", - "@sveltejs/vite-plugin-svelte": "^6.2.1", - "@tailwindcss/forms": "^0.5.9", - "@tailwindcss/typography": "^0.5.15", - "@tailwindcss/vite": "^4.0.0", + "@chromatic-com/storybook": "5.0.0", + "@eslint/compat": "1.4.1", + "@eslint/js": "9.39.2", + "@internationalized/date": "3.10.1", + "@lucide/svelte": "0.515.0", + "@modelcontextprotocol/sdk": "1.26.0", + "@playwright/test": "1.56.1", + "@storybook/addon-a11y": "10.2.4", + "@storybook/addon-docs": "10.2.4", + "@storybook/addon-svelte-csf": "5.0.10", + "@storybook/addon-vitest": "10.2.4", + "@storybook/sveltekit": "10.2.4", + "@sveltejs/adapter-static": "3.0.10", + "@sveltejs/kit": "2.60.1", + "@sveltejs/vite-plugin-svelte": "6.2.1", + "@tailwindcss/forms": "0.5.10", + "@tailwindcss/typography": "0.5.16", + "@tailwindcss/vite": "4.1.11", "@types/node": "^24", - "@vitest/browser": "^3.2.3", - "@vitest/coverage-v8": "^3.2.3", - "bits-ui": "^2.14.4", - "clsx": "^2.1.1", - "dexie": "^4.0.11", - "eslint": "^9.18.0", - "eslint-config-prettier": "^10.0.1", - "eslint-plugin-storybook": "^10.2.4", - "eslint-plugin-svelte": "^3.0.0", - "globals": "^16.0.0", - "http-server": "^14.1.1", - "mdast": "^3.0.0", - "mdsvex": "^0.12.3", - "playwright": "^1.56.1", - "prettier": "^3.4.2", - "prettier-plugin-svelte": "^3.3.3", - "prettier-plugin-tailwindcss": "^0.6.11", - "rehype-katex": "^7.0.1", - "remark-math": "^6.0.0", - "sass": "^1.93.3", - "storybook": "^10.2.4", - "svelte": "^5.38.2", - "svelte-check": "^4.0.0", - "tailwind-merge": "^3.3.1", - "tailwind-variants": "^3.2.2", - "tailwindcss": "^4.0.0", - "tw-animate-css": "^1.3.5", - "typescript": "^5.0.0", - "typescript-eslint": "^8.20.0", - "unified": "^11.0.5", - "uuid": "^13.0.0", - "vite": "^7.2.2", - "vite-plugin-devtools-json": "^0.2.0", - "vitest": "^3.2.3", - "vitest-browser-svelte": "^0.1.0" + "@vitest/browser": "4.1.8", + "@vitest/browser-playwright": "4.1.8", + "@vitest/coverage-v8": "4.1.8", + "bits-ui": "2.18.1", + "clsx": "2.1.1", + "dexie": "4.0.11", + "eslint": "9.39.2", + "eslint-config-prettier": "10.1.8", + "eslint-plugin-storybook": "10.2.4", + "eslint-plugin-svelte": "3.15.0", + "globals": "16.3.0", + "highlight.js": "11.11.1", + "http-server": "14.1.1", + "mdast": "3.0.0", + "mdsvex": "0.12.6", + "mermaid": "11.15.0", + "mode-watcher": "1.1.0", + "pdfjs-dist": "5.4.54", + "playwright": "1.56.1", + "prettier": "3.6.2", + "prettier-plugin-svelte": "3.4.0", + "prettier-plugin-tailwindcss": "0.6.14", + "rehype-highlight": "7.0.2", + "rehype-katex": "7.0.1", + "rehype-stringify": "10.0.1", + "remark": "15.0.1", + "remark-breaks": "4.0.0", + "remark-gfm": "4.0.1", + "remark-html": "16.0.1", + "remark-math": "6.0.0", + "remark-rehype": "11.1.2", + "sass": "1.93.3", + "storybook": "10.3.3", + "svelte": "5.55.7", + "svelte-check": "4.3.0", + "svelte-sonner": "1.0.5", + "tailwind-merge": "3.3.1", + "tailwind-variants": "3.2.2", + "tailwindcss": "4.1.11", + "tw-animate-css": "1.3.5", + "typescript": "5.8.3", + "typescript-eslint": "8.56.0", + "unified": "11.0.5", + "unist-util-visit": "5.0.0", + "uuid": "13.0.2", + "vite": "7.3.2", + "vite-plugin-devtools-json": "0.2.1", + "vitest": "4.1.8", + "vitest-browser-svelte": "2.1.1", + "zod": "4.2.1" }, - "dependencies": { - "@modelcontextprotocol/sdk": "^1.25.1", - "highlight.js": "^11.11.1", - "mermaid": "^11.15.0", - "mode-watcher": "^1.1.0", - "pdfjs-dist": "^5.4.54", - "rehype-highlight": "^7.0.2", - "rehype-stringify": "^10.0.1", - "remark": "^15.0.1", - "remark-breaks": "^4.0.0", - "remark-gfm": "^4.0.1", - "remark-html": "^16.0.1", - "remark-rehype": "^11.1.2", - "svelte-sonner": "^1.0.5", - "unist-util-visit": "^5.0.0", - "zod": "^4.2.1" + "overrides": { + "cookie": "1.1.1" } } diff --git a/tools/ui/src/lib/components/app/actions/ActionIcon.svelte b/tools/ui/src/lib/components/app/actions/ActionIcon.svelte index 849b83b19c81..f156df66998a 100644 --- a/tools/ui/src/lib/components/app/actions/ActionIcon.svelte +++ b/tools/ui/src/lib/components/app/actions/ActionIcon.svelte @@ -35,23 +35,27 @@ - + onclick?.(e); + }} + class="h-6 w-6 p-0 {className} flex hover:bg-transparent data-[state=open]:bg-transparent!" + aria-label={ariaLabel || tooltip} + > + {#if icon} + {@const IconComponent = icon} + + {/if} + + {/snippet} diff --git a/tools/ui/src/lib/components/app/badges/BadgeInfo.svelte b/tools/ui/src/lib/components/app/badges/BadgeInfo.svelte index 25986082bea5..c87c94bc4770 100644 --- a/tools/ui/src/lib/components/app/badges/BadgeInfo.svelte +++ b/tools/ui/src/lib/components/app/badges/BadgeInfo.svelte @@ -1,22 +1,22 @@ - - - -

Reading (prompt processing)

- - - {/if} - - +{#snippet viewButton(opts: { + view: ChatMessageStatsView; + icon: Component; + label: string; + tooltipText: string; + disabled?: boolean; +})} + {@const IconComponent = opts.icon} + + + + {#snippet child({ props })} - + {/snippet} + - -

- {isGenerationDisabled - ? 'Generation (waiting for tokens...)' - : 'Generation (token output)'} -

- - + +

{opts.tooltipText}

+ + +{/snippet} - {#if hasAgenticStats} - - - - + {@render viewButton({ + view: ChatMessageStatsView.GENERATION, + icon: Sparkles, + label: 'Generation', + tooltipText: isGenerationDisabled + ? 'Generation (waiting for tokens...)' + : 'Generation (token output)', + disabled: isGenerationDisabled + })} - -

Tool calls

- - + {#if hasAgenticStats} + {@render viewButton({ + view: ChatMessageStatsView.TOOLS, + icon: Wrench, + label: 'Tools', + tooltipText: 'Tool calls' + })} {#if !hideSummary} - - - - - - -

Agentic summary

- - + {@render viewButton({ + view: ChatMessageStatsView.SUMMARY, + icon: Layers, + label: 'Summary', + tooltipText: 'Agentic summary' + })} {/if} {/if} diff --git a/tools/ui/src/lib/components/app/chat/ChatMessages/ChatMessageStatistics/ChatMessageStatisticsBadge.svelte b/tools/ui/src/lib/components/app/chat/ChatMessages/ChatMessageStatistics/ChatMessageStatisticsBadge.svelte index eea7da7b2f10..db7d01690a56 100644 --- a/tools/ui/src/lib/components/app/chat/ChatMessages/ChatMessageStatistics/ChatMessageStatisticsBadge.svelte +++ b/tools/ui/src/lib/components/app/chat/ChatMessages/ChatMessageStatistics/ChatMessageStatisticsBadge.svelte @@ -21,13 +21,16 @@ {#if tooltipLabel} - - {#snippet icon()} - - {/snippet} + + {#snippet child({ props })} + + {#snippet icon()} + + {/snippet} - {value} - + {value} + + {/snippet}

{tooltipLabel}

diff --git a/tools/ui/src/lib/components/app/chat/ChatScreen/ChatScreenActionScrollDown.svelte b/tools/ui/src/lib/components/app/chat/ChatScreen/ChatScreenActionScrollDown.svelte index c43bee3e3c3d..a22c491adac6 100644 --- a/tools/ui/src/lib/components/app/chat/ChatScreen/ChatScreenActionScrollDown.svelte +++ b/tools/ui/src/lib/components/app/chat/ChatScreen/ChatScreenActionScrollDown.svelte @@ -41,16 +41,13 @@ }); -
+
+ {/snippet} + - {#if ms.updating} - + {#if selectedOption} + +

{selectedOption.model}

+ {/if} - + {/if} {/if}
diff --git a/tools/ui/src/lib/components/app/navigation/DropdownMenuActions.svelte b/tools/ui/src/lib/components/app/navigation/DropdownMenuActions.svelte index 83d856d10eaa..951831149fc9 100644 --- a/tools/ui/src/lib/components/app/navigation/DropdownMenuActions.svelte +++ b/tools/ui/src/lib/components/app/navigation/DropdownMenuActions.svelte @@ -34,24 +34,28 @@ - e.stopPropagation()} - > - {#if triggerTooltip} - - + + + + {#snippet child({ props })} + e.stopPropagation()} + > {@render iconComponent(triggerIcon, 'h-3 w-3')} - {triggerTooltip} - - -

{triggerTooltip}

- - - {:else} - {@render iconComponent(triggerIcon, 'h-3 w-3')} + {#if triggerTooltip} + {triggerTooltip} + {/if} + + {/snippet} + + {#if triggerTooltip} + +

{triggerTooltip}

+ {/if} - + {#each actions as action, index (action.label)} diff --git a/tools/ui/src/lib/components/app/navigation/SidebarNavigation/SidebarNavigationConversationItem.svelte b/tools/ui/src/lib/components/app/navigation/SidebarNavigation/SidebarNavigationConversationItem.svelte index dad8d954cbb2..e38a937385a3 100644 --- a/tools/ui/src/lib/components/app/navigation/SidebarNavigation/SidebarNavigationConversationItem.svelte +++ b/tools/ui/src/lib/components/app/navigation/SidebarNavigation/SidebarNavigationConversationItem.svelte @@ -105,6 +105,12 @@ onclick={handleSelect} onmouseover={handleMouseOver} onmouseleave={handleMouseLeave} + onfocusin={handleMouseOver} + onfocusout={(e) => { + if (!e.currentTarget.contains(e.relatedTarget as Node | null)) { + handleMouseLeave(); + } + }} >
0} - - - + + {#snippet child({ props })} + + + + {/snippet} @@ -195,7 +205,8 @@ opacity: 0; } - &:is(:hover) :global([data-slot='dropdown-menu-trigger']) { + &:is(:hover) :global([data-slot='dropdown-menu-trigger']), + &:focus-within :global([data-slot='dropdown-menu-trigger']) { opacity: 1; } @media (max-width: 768px) { diff --git a/tools/ui/src/lib/constants/formatters.ts b/tools/ui/src/lib/constants/formatters.ts index d6d1b883ffe9..c417faea43d9 100644 --- a/tools/ui/src/lib/constants/formatters.ts +++ b/tools/ui/src/lib/constants/formatters.ts @@ -6,3 +6,30 @@ export const MEDIUM_DURATION_THRESHOLD = 10; /** Default display value when no performance time is available */ export const DEFAULT_PERFORMANCE_TIME = '0s'; + +/** Max length before reasoning preview is truncated */ +export const MAX_PREVIEW_LENGTH = 120; + +export const STRIP_MARKDOWN_CAPTURE_PATTERNS: [RegExp, string][] = [ + [/^```(.*)/gm, '$1'], + [/(.*)```$/gm, '$1'], + [/`([^`]*)`/g, '$1'], + [/\*\*(.*?)\*\*/g, '$1'], + [/__(.*?)__/g, '$1'], + [/\*(.*?)\*/g, '$1'], + [/_(.*?)_/g, '$1'] +]; + +/* eslint-disable no-misleading-character-class */ +export const STRIP_MARKDOWN_INLINE_REGEX = new RegExp( + [ + '<[^>]*>', + '^>\\s*', + '^#{1,6}\\s+', + '^[\\s]*[-*+]\\s+', + '^[\\s]*\\d+[.)]\\s+', + '[\\u{1F600}-\\u{1F64F}\\u{1F300}-\\u{1F5FF}\\u{1F680}-\\u{1F6FF}\\u{1F1E0}-\\u{1F1FF}\\u{2600}-\\u{26FF}\\u{2700}-\\u{27BF}\\u{FE00}-\\u{FE0F}\\u{1F900}-\\u{1F9FF}\\u{1FA00}-\\u{1FA6F}\\u{1FA70}-\\u{1FAFF}\\u{200D}\\u{20E3}\\u{231A}-\\u{231B}\\u{23E9}-\\u{23F3}\\u{23F8}-\\u{23FA}\\u{25AA}-\\u{25AB}\\u{25B6}\\u{25C0}\\u{25FB}-\\u{25FE}\\u{2934}-\\u{2935}\\u{2B05}-\\u{2B07}\\u{2B1B}-\\u{2B1C}\\u{2B50}\\u{2B55}\\u{3030}\\u{303D}\\u{3297}\\u{3299}]' + ].join('|'), + 'gmu' +); +/* eslint-enable no-misleading-character-class */ diff --git a/tools/ui/src/lib/hooks/use-throttle.svelte.ts b/tools/ui/src/lib/hooks/use-throttle.svelte.ts new file mode 100644 index 000000000000..0795519787b8 --- /dev/null +++ b/tools/ui/src/lib/hooks/use-throttle.svelte.ts @@ -0,0 +1,32 @@ +/** + * Creates a reactive throttle key that increments when `getValue()` changes + * and the throttle window has elapsed since the last increment. + * + * Useful for throttling animations that should not fire on every rapid update. + * + * @param getValue - A reactive getter for the value to watch + * @param ms - Throttle window in milliseconds + * @returns A reactive number that increments when the throttled value changes + */ +export function useThrottle(getValue: () => string | undefined, ms: number) { + let key = $state(0); + let throttleEnd = $state(0); + let lastValue: string | undefined = getValue(); + + $effect(() => { + const value = getValue(); + if (value === lastValue) return; + const now = Date.now(); + if (now >= throttleEnd) { + lastValue = value; + key++; + throttleEnd = now + ms; + } + }); + + return { + get key() { + return key; + } + }; +} diff --git a/tools/ui/src/lib/utils/agentic.ts b/tools/ui/src/lib/utils/agentic.ts index 52ff35793063..d19f03434e6b 100644 --- a/tools/ui/src/lib/utils/agentic.ts +++ b/tools/ui/src/lib/utils/agentic.ts @@ -18,6 +18,7 @@ export interface AgenticSection { toolArgs?: string; toolResult?: string; toolResultExtras?: DatabaseMessageExtra[]; + wasInterrupted?: boolean; } /** @@ -51,7 +52,8 @@ function deriveSingleTurnSections( const isPending = isStreaming && !hasContentAfterReasoning; sections.push({ type: isPending ? AgenticSectionType.REASONING_PENDING : AgenticSectionType.REASONING, - content: message.reasoningContent + content: message.reasoningContent, + wasInterrupted: !isStreaming && !hasContentAfterReasoning }); } diff --git a/tools/ui/src/lib/utils/formatters.ts b/tools/ui/src/lib/utils/formatters.ts index 24a2c1c94c18..de74ee8686d1 100644 --- a/tools/ui/src/lib/utils/formatters.ts +++ b/tools/ui/src/lib/utils/formatters.ts @@ -3,7 +3,11 @@ import { SECONDS_PER_MINUTE, SECONDS_PER_HOUR, SHORT_DURATION_THRESHOLD, - MEDIUM_DURATION_THRESHOLD + MEDIUM_DURATION_THRESHOLD, + MAX_PREVIEW_LENGTH, + STRIP_MARKDOWN_INLINE_REGEX, + STRIP_MARKDOWN_CAPTURE_PATTERNS, + NEWLINE_SEPARATOR } from '$lib/constants'; /** @@ -151,3 +155,33 @@ export function formatAttachmentText( const header = extra ? `${name} (${extra})` : name; return `\n\n--- ${label}: ${header} ---\n${content}`; } + +export function formatReasoningPreview(content: string): { preview: string; overflow: number } { + if (!content) return { preview: '', overflow: 0 }; + + const lines = content.split(NEWLINE_SEPARATOR); + let lastLine = ''; + + for (let i = lines.length - 1; i >= 0; i--) { + let cleaned = lines[i].trim(); + if (!cleaned) continue; + + cleaned = cleaned.replace(STRIP_MARKDOWN_INLINE_REGEX, ''); + for (const [pattern, replacement] of STRIP_MARKDOWN_CAPTURE_PATTERNS) { + cleaned = cleaned.replace(pattern, replacement); + } + + if (cleaned.length > 0) { + lastLine = cleaned; + break; + } + } + + const fullLength = lastLine.length; + const overflow = Math.max(0, fullLength - MAX_PREVIEW_LENGTH); + if (fullLength > MAX_PREVIEW_LENGTH) { + lastLine = lastLine.slice(0, MAX_PREVIEW_LENGTH) + '...'; + } + + return { preview: lastLine, overflow }; +} diff --git a/tools/ui/src/lib/utils/index.ts b/tools/ui/src/lib/utils/index.ts index 00aa49c41765..637db8812c4d 100644 --- a/tools/ui/src/lib/utils/index.ts +++ b/tools/ui/src/lib/utils/index.ts @@ -76,7 +76,8 @@ export { formatJsonPretty, formatTime, formatPerformanceTime, - formatAttachmentText + formatAttachmentText, + formatReasoningPreview } from './formatters'; // IME utilities diff --git a/tools/ui/tests/stories/SidebarNavigation.stories.svelte b/tools/ui/tests/stories/SidebarNavigation.stories.svelte index f64ee4f9b551..aae42f2a053c 100644 --- a/tools/ui/tests/stories/SidebarNavigation.stories.svelte +++ b/tools/ui/tests/stories/SidebarNavigation.stories.svelte @@ -58,10 +58,12 @@ name="Default" play={async () => { const { conversationsStore } = await import('$lib/stores/conversations.svelte'); - - waitFor(() => setTimeout(() => { - conversationsStore.conversations = mockConversations; - }, 0)); + + waitFor(() => + setTimeout(() => { + conversationsStore.conversations = mockConversations; + }, 0) + ); }} > @@ -76,11 +78,13 @@ name="SearchActive" play={async ({ userEvent }) => { const { conversationsStore } = await import('$lib/stores/conversations.svelte'); - - waitFor(() => setTimeout(() => { - conversationsStore.conversations = mockConversations; - }, 0)); - + + waitFor(() => + setTimeout(() => { + conversationsStore.conversations = mockConversations; + }, 0) + ); + const searchTrigger = screen.getByText('Search'); userEvent.click(searchTrigger); }} diff --git a/tools/ui/tests/stories/a11y/ActionIcon.a11y.stories.svelte b/tools/ui/tests/stories/a11y/ActionIcon.a11y.stories.svelte new file mode 100644 index 000000000000..20f5e057b0c7 --- /dev/null +++ b/tools/ui/tests/stories/a11y/ActionIcon.a11y.stories.svelte @@ -0,0 +1,34 @@ + + + { + const before = await canvas.findByRole('button', { name: 'before' }); + const target = await canvas.findByRole('button', { name: 'Copy' }); + + before.focus(); + await userEvent.tab(); + + await expect(target).toHaveFocus(); + }} +> +
+ + {}} /> +
+ diff --git a/tools/ui/tests/stories/a11y/ChatMessageStatistics.a11y.stories.svelte b/tools/ui/tests/stories/a11y/ChatMessageStatistics.a11y.stories.svelte new file mode 100644 index 000000000000..4aaf60cd6560 --- /dev/null +++ b/tools/ui/tests/stories/a11y/ChatMessageStatistics.a11y.stories.svelte @@ -0,0 +1,50 @@ + + + { + const reading = await canvas.findByRole('button', { name: 'Reading' }); + const generation = await canvas.findByRole('button', { name: 'Generation' }); + const tools = await canvas.findByRole('button', { name: 'Tools' }); + const summary = await canvas.findByRole('button', { name: 'Summary' }); + + reading.focus(); + await expect(reading).toHaveFocus(); + + await userEvent.tab(); + await expect(generation).toHaveFocus(); + + await userEvent.tab(); + await expect(tools).toHaveFocus(); + + await userEvent.tab(); + await expect(summary).toHaveFocus(); + }} +/> diff --git a/tools/ui/tests/stories/ChatScreenForm.a11y.stories.svelte b/tools/ui/tests/stories/a11y/ChatScreenForm.a11y.stories.svelte similarity index 100% rename from tools/ui/tests/stories/ChatScreenForm.a11y.stories.svelte rename to tools/ui/tests/stories/a11y/ChatScreenForm.a11y.stories.svelte diff --git a/tools/ui/tests/stories/a11y/HorizontalScrollCarousel.a11y.stories.svelte b/tools/ui/tests/stories/a11y/HorizontalScrollCarousel.a11y.stories.svelte new file mode 100644 index 000000000000..937d7ab10949 --- /dev/null +++ b/tools/ui/tests/stories/a11y/HorizontalScrollCarousel.a11y.stories.svelte @@ -0,0 +1,69 @@ + + + { + const before = await canvas.findByRole('button', { name: 'before' }); + const after = await canvas.findByRole('button', { name: 'after' }); + const leftArrow = await canvas.findByRole('button', { name: 'Scroll left' }); + + await waitFor(() => { + expect(leftArrow).toBeDisabled(); + }); + + before.focus(); + await userEvent.tab(); + + await expect(after).toHaveFocus(); + }} +> +
+ + +
+
+ + +
+ + + { + const before = await canvas.findByRole('button', { name: 'before' }); + const rightArrow = await canvas.findByRole('button', { name: 'Scroll right' }); + + await waitFor(() => { + expect(rightArrow).not.toBeDisabled(); + }); + + before.focus(); + await userEvent.tab(); + + await expect(rightArrow).toHaveFocus(); + }} +> +
+ + + {#each [...Array(20).keys()] as i (i)} +
{i}
+ {/each} + +
+ diff --git a/tools/ui/tests/stories/a11y/SidebarNavigationConversationItem.a11y.stories.svelte b/tools/ui/tests/stories/a11y/SidebarNavigationConversationItem.a11y.stories.svelte new file mode 100644 index 000000000000..1fc42608f720 --- /dev/null +++ b/tools/ui/tests/stories/a11y/SidebarNavigationConversationItem.a11y.stories.svelte @@ -0,0 +1,36 @@ + + + { + const row = await canvas.findByRole('button', { name: /Forked Conversation/ }); + const forkIcon = await canvas.findByRole('link'); + + row.focus(); + await userEvent.tab(); + + await expect(forkIcon).toHaveFocus(); + }} +/> diff --git a/tools/ui/vite.config.ts b/tools/ui/vite.config.ts index 5b57eae3ad54..13e889dbc101 100644 --- a/tools/ui/vite.config.ts +++ b/tools/ui/vite.config.ts @@ -7,11 +7,23 @@ import { defineConfig, searchForWorkspaceRoot } from 'vite'; import devtoolsJson from 'vite-plugin-devtools-json'; import { storybookTest } from '@storybook/addon-vitest/vitest-plugin'; import { llamaCppBuildPlugin } from './scripts/vite-plugin-llama-cpp-build'; +import { playwright } from '@vitest/browser-playwright'; const __dirname = dirname(fileURLToPath(import.meta.url)); const SERVER_ORIGIN = import.meta.env?.VITE_PUBLIC_SERVER_ORIGIN || 'http://localhost:8080'; +// eslint-disable-next-line @typescript-eslint/no-explicit-any +const browserBaseConfig: any = { + enabled: true, + provider: playwright({ + launchOptions: { + args: ['--no-sandbox'] + } + }), + instances: [{ browser: 'chromium' }] +}; + export default defineConfig({ resolve: { alias: { @@ -33,12 +45,7 @@ export default defineConfig({ extends: './vite.config.ts', test: { name: 'client', - environment: 'browser', - browser: { - enabled: true, - provider: 'playwright', - instances: [{ browser: 'chromium' }] - }, + browser: browserBaseConfig, include: ['tests/client/**/*.svelte.{test,spec}.{js,ts}'], setupFiles: ['./vitest-setup-client.ts'] } @@ -57,13 +64,7 @@ export default defineConfig({ extends: './vite.config.ts', test: { name: 'ui', - environment: 'browser', - browser: { - enabled: true, - provider: 'playwright', - instances: [{ browser: 'chromium', headless: true }] - }, - include: ['tests/stories/**/*.stories.{js,ts,svelte}'], + browser: { ...browserBaseConfig, instances: [{ browser: 'chromium', headless: true }] }, setupFiles: ['./.storybook/vitest.setup.ts'] }, plugins: [