diff --git a/configs/amd-master.yaml b/configs/amd-master.yaml index 2e4be44b36..4260b43bfa 100644 --- a/configs/amd-master.yaml +++ b/configs/amd-master.yaml @@ -404,7 +404,7 @@ qwen3.5-fp8-mi355x-atom-mtp: - { tp: 8, ep: 1, conc-start: 4, conc-end: 256, spec-decoding: mtp } qwen3.5-fp8-mi355x-sglang-disagg: - image: lmsysorg/sglang-rocm:v0.5.11-rocm700-mi35x-20260511 + image: lmsysorg/sglang:v0.5.14-rocm720-mi35x model: Qwen/Qwen3.5-397B-A17B-FP8 model-prefix: qwen3.5 runner: mi355x-disagg @@ -421,7 +421,7 @@ qwen3.5-fp8-mi355x-sglang-disagg: search-space: # Matches qwen3.5-fp8-mi355x-sglang TP8/EP1 low-concurrency sweep - spec-decoding: "none" - conc-list: [ 8, 16, 32, 64, 128, 256, 512 ] + conc-list: [ 8, 16, 32, 64, 128 ] prefill: num-worker: 1 tp: 8 @@ -452,7 +452,7 @@ qwen3.5-fp8-mi355x-sglang-disagg: # MoRI is added to is_deepep_class_backend() or shared-slot # accounting is reconciled. - spec-decoding: "none" - conc-list: [ 8, 16, 32, 64, 128, 256, 512 ] + conc-list: [ 8, 16, 32, 64, 128 ] prefill: num-worker: 1 tp: 8 diff --git a/configs/runners.yaml b/configs/runners.yaml index 93da791b85..1386652f5a 100644 --- a/configs/runners.yaml +++ b/configs/runners.yaml @@ -126,6 +126,12 @@ labels: - mi355x-amds_06 - mi355x-amds_07 - mi355x-amds_08 + - mi355x-amds_12 + - mi355x-amds_14 + - mi355x-amds_16 + - mi355x-amds_17 + - mi355x-amds_18 + - mi355x-amds_19 gb200: - gb200-nv_0 - gb200-nv_1 diff --git a/perf-changelog.yaml b/perf-changelog.yaml index c620aceaa5..6fdff162db 100644 --- a/perf-changelog.yaml +++ b/perf-changelog.yaml @@ -4918,3 +4918,12 @@ - "Image: vllm/vllm-openai:nightly-dev-x86_64-cu13.0.1-904e4ec" - "B300: GPU-resident TP4/TP8 at conc [1,2,4,6,8,12,16,20,24,28,32] and DEP8 at conc [32,64,96,128,160,192,196,224,228] (max-num-batched-tokens 16384, long-prefill-token-threshold 4096, gpu-memory-utilization 0.92); TP4 SimpleCPU lazy-offload at conc [28,32,36,40]; DEP4 at conc [8,16,24,32,40,48,56,64,72] with both SimpleCPU and Mooncake 0.3.11.post1." pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2241 + +- config-keys: + - qwen3.5-fp8-mi355x-sglang-disagg + description: + - "Bump Qwen3.5-FP8 MI355X SGLang disagg image from lmsysorg/sglang-rocm:v0.5.11-rocm700-mi35x-20260511 to lmsysorg/sglang:v0.5.14-rocm720-mi35x (ROCm 7.0 → 7.2, sglang v0.5.11 → v0.5.14)." + - "Fix disagg SLURM exclude list: add mia1-p01-g09 (broken pyxis) to submit.sh — was missing from multi-node path, causing prefill worker 503 failures." + - "Expand mi355x-disagg runner pool from 3 to 9 nodes." + - "Concurrency sweep: 1K1K and 8K1K both [ 8, 16, 32, 64, 128 ]." + pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2094