3 people f98ae6a9fd [Bugfix][Core] Keep resumable sessions that stop while preempted (#58778) ...

Signed-off-by: David Cheung <d7cheung@gmail.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: Yifan Zong <yzong@redhat.com>

2026-10-17 09:08:14 +00:00

..

__init__.py

[Feature] Add External LB Mode Support for Elastic EP Scaling (#43202)

2026-10-15 21:29:02 -04:00

admission_control.py

[Frontend] Share max_num_queued_reqs across API server processes (#54746)

2026-09-15 14:50:26 +00:00

async_llm.py

[Bugfix][Core] Keep resumable sessions that stop while preempted (#58778)

2026-10-17 09:08:14 +00:00

coordinator.py

[DP] Engines own wave wake-ups; drop the front-end FIRST_REQ (#59559)

2026-10-16 19:41:54 -04:00

core_client.py

[DP] Engines own wave wake-ups; drop the front-end FIRST_REQ (#59559)

2026-10-16 19:41:54 -04:00

core.py

[DP] Engines own wave wake-ups; drop the front-end FIRST_REQ (#59559)

2026-10-16 19:41:54 -04:00

detokenizer.py

[Bugfix][Spec Decode] Trim token_ids/logprobs left past a stop string under speculative decoding (#47616)

2026-10-09 14:22:31 -07:00

exceptions.py

[Frontend] Clean Client Facing 500 Report (#58043)

2026-10-14 14:27:58 -04:00

input_processor.py

[watermark] compatibility validation (#56801)

2026-10-05 14:37:13 -04:00

llm_engine.py

[RL][Frontend] Return token-level weight-version spans on final outputs (#59582)

2026-10-11 11:33:29 +08:00

logprobs.py

[Feature] Add fixed-token prefill scoring (#54335)

2026-09-28 07:50:09 -07:00

output_processor.py

[Bugfix][Frontend] Preserve streaming chunk boundaries in RequestOutputCollector (#58941)

2026-10-15 16:38:28 +00:00

parallel_sampling.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

tensor_ipc.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

utils.py

[Feature] Add External LB Mode Support for Elastic EP Scaling (#43202)

2026-10-15 21:29:02 -04:00