Jialin Ouyang 201c971e96 [Perf][Easy] Early stop in request_block_hasher (#26112) ...

Signed-off-by: Jialin Ouyang <Jialin.Ouyang@gmail.com>

2025-10-05 16:46:03 +08:00

..

attention

[CPU] Refine batch reorder of CPU attention backend (#26096)

2025-10-04 21:54:35 +08:00

core

[Perf][Easy] Early stop in request_block_hasher (#26112)

2025-10-05 16:46:03 +08:00

engine

[Renderer] Move Processor out of LLMEngine (#26165)

2025-10-03 15:08:22 +00:00

executor

[V0 Deprecation] Remove vllm.worker and update according imports (#25901)

2025-09-29 23:26:11 +00:00

kv_offload

[Docs] Enable fail_on_warning for the docs build in CI (#25580)

2025-09-24 19:30:33 +00:00

metrics

[Easy] Add str repr for IterationStats (#26232)

2025-10-05 05:00:21 +00:00

pool

[Performance] V1 Pooling Models E2E Performance Optimization (#23162)

2025-08-21 13:26:09 +00:00

sample

[Perf] Remove hardcoded num_warps=1 (#26183)

2025-10-03 20:38:50 +00:00

spec_decode

[Model] MTP fallback to eager for DeepSeek v32 (#25982)

2025-10-01 01:53:22 +00:00

structured_output

[Build] Update Xgrammar to 0.1.25 (#25467)

2025-09-23 21:25:46 +00:00

worker

[CPU] Refine batch reorder of CPU attention backend (#26096)

2025-10-04 21:54:35 +08:00

__init__.py

[V1] AsyncLLM Implementation (#9826)

2024-11-11 23:05:38 +00:00

cudagraph_dispatcher.py

Remove redundant cudagraph dispatcher warning (#25841)

2025-09-28 17:12:42 -04:00

kv_cache_interface.py

[V1] [Hybrid] Mamba2 Automatic Prefix Caching (#25752)

2025-10-04 06:34:22 +02:00

outputs.py

[V1] [P/D] Add Support for KV Load Failure Recovery (#19330)

2025-09-30 14:57:08 -07:00

request.py

[Core] Don't count preempted tokens in prefix cache hit rate (#25787)

2025-09-27 00:16:40 +00:00

serial_utils.py

fix: revert cast to cpu in MsgpackEncoder._encode_tensor to avoid hidden performance regressions (#25738)

2025-09-26 01:18:05 -07:00

utils.py

[Bugfix] Optimize CpuGpuBuffer initialization (#25447)

2025-09-27 08:07:36 +08:00