SunLei 3d74a4baf6 [Cherry-Pick] MTP split draft_tokens into standalone post-processing path(#5205) (#5231) ...

* refactor(mtp): split draft_tokens into standalone post-processing path for MTP + logprobs

* Restore Request.__repr__ implementation

* ci

* add envs

* fix unittest

2025-11-27 11:23:38 +08:00

..

tool_parsers

[Feature] Unify the registration name recognition for tool_parser and reasoning_parser to “-” (#4668)

2025-10-31 10:45:27 +08:00

__init__.py

polish code with new pre-commit rule (#2923)

2025-07-19 23:19:27 +08:00

api_server.py

[Feature] support eplb in api_server (#4782)

2025-11-24 20:22:29 +08:00

middleware.py

[Feature] Enable FastDeploy to support adding the “--api-key” authentication parameter. (#4806)

2025-11-08 18:24:02 +08:00

multi_api_server.py

[Fix] fix multi api server log dir (#3967)

2025-09-10 17:15:30 +08:00

protocol.py

[Feature] [PD] add simple router and refine splitwise deployment (#4709)

2025-11-06 14:56:02 +08:00

response_processors.py

feat: add support for API usage with multimodal models (#4548)

2025-10-28 20:23:46 +08:00

run_batch.py

[Feature] support eplb in api_server (#4782)

2025-11-24 20:22:29 +08:00

serving_chat.py

[Cherry-Pick] MTP split draft_tokens into standalone post-processing path(#5205) (#5231)

2025-11-27 11:23:38 +08:00

serving_completion.py

[BugFix] unify max_tokens (#4968)

2025-11-18 20:01:33 +08:00

serving_embedding.py

feat: add post-processing step for pool_output (#4462)

2025-10-21 20:24:26 +08:00

serving_engine.py

feat: add post-processing step for pool_output (#4462)

2025-10-21 20:24:26 +08:00

serving_models.py

Bugfix test exception (#4171)

2025-09-19 11:48:49 +08:00

serving_reward.py

[feature] support reward api (#4518)

2025-10-29 00:20:28 +08:00

test_openai.py

polish code with new pre-commit rule (#2923)

2025-07-19 23:19:27 +08:00

usage_calculator.py

feat: add support for API usage with multimodal models (#4548)

2025-10-28 20:23:46 +08:00

utils.py

[APIServer] metrics use port the same as api_port (#5016)

2025-11-17 10:42:45 +08:00