-
Notifications
You must be signed in to change notification settings - Fork 708
Pull requests: PaddlePaddle/FastDeploy
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
Revert "[Cherry-Pick] [Bug Fix] Fix MM mtp incorrect rope emb(#6581)"
#6633
opened Mar 3, 2026 by
ming1753
Loading…
[Cherry-Pick][BugFix] Fix exist_prefill_flag when preempted task exist (#6629)
#6630
opened Mar 3, 2026 by
Sunny-bot1
Loading…
5 tasks
[BugFix] Fix exist_prefill_flag when preempted task exist
#6629
opened Mar 3, 2026 by
Sunny-bot1
Loading…
5 tasks
[benchmark]Improve file opening with encoding and error handling
contributor
External developers
#6628
opened Mar 3, 2026 by
plusNew001
Loading…
5 tasks
[XPU] Add speculate_limit_thinking_content_length Op.
#6627
opened Mar 3, 2026 by
Jiajun-Ji
Loading…
5 tasks
[Cherry-Pick] [BugFix] Fix inaccurate cache hit rate and TTFT after request preemption
#6626
opened Mar 3, 2026 by
liyonghua0910
Loading…
5 tasks
[Feature][Models] Support Deepseekv3.2 model and dsa-indexer networking to FastDeploy
#6625
opened Mar 3, 2026 by
chang-wenbin
Loading…
5 tasks
[Style] Apply clang-format to .cu/.cuh/.h/.cc files
#6623
opened Mar 3, 2026 by
gongweibao
Loading…
5 tasks done
[BugFix] Fix inaccurate cache hit rate and TTFT after request preemption
#6620
opened Mar 3, 2026 by
liyonghua0910
Loading…
5 tasks
[BugFix] Fix platform-specific attribute access in reset_model_inputs
#6614
opened Mar 2, 2026 by
kevincheng2
Loading…
1 of 5 tasks
[XPU] Add XPU support for speculate_save_output_with_topk.
#6611
opened Mar 2, 2026 by
Jiajun-Ji
Loading…
5 tasks
[Feature][BugFix][OP] Enhance Deterministic Inference Mode with Kernel-level Fixes and Batch-invariant BMM
#6610
opened Mar 2, 2026 by
gongweibao
Loading…
5 tasks done
feat(scheduler): implement SGLang-style dynamic resource management and preemption
contributor
External developers
#6606
opened Mar 2, 2026 by
Foriv
Loading…
[RL]Perf: Optimize batch delete prefix and fused put in R3
#6604
opened Mar 2, 2026 by
gongshaotian
Loading…
5 of 6 tasks
[XPU] Add logprob support OPs for speculative decoding.
#6603
opened Mar 2, 2026 by
Jiajun-Ji
Loading…
5 tasks
[Cherry-Pick] [RL] Support SM100 FP8 quantization in RL #6601
#6602
opened Mar 2, 2026 by
bukejiyu
Loading…
5 tasks
[RL] Support SM100 FP8 quantization in RL
#6601
opened Mar 2, 2026 by
bukejiyu
Loading…
1 of 5 tasks
[RL][Cherry-Pick] Support Fully Async and PrefixCache
#6599
opened Mar 2, 2026 by
gongshaotian
Loading…
5 tasks done
[BugFix] fix dp sheduler bug in ep4tp1 when start by using multi_api_server
#6598
opened Mar 2, 2026 by
ddchenhao66
Loading…
5 tasks
Previous Next
ProTip!
What’s not been updated in a month: updated:<2026-02-03.