qwes5s5 b3ca7f041a [BugFix] Fix redundant prompt_logprobs in the second chunk of streaming response when return_token_ids is enabled for v1/completions and fix trace file name (#5829) ...

* fix prompt logprobs bug

* fix trace file name

---------

Co-authored-by: qwes5s5 <root@yq01-sys-rpm26xc1knu.yq01.baidu.com>

2026-01-06 14:11:43 +08:00

..

tool_parsers

…

v1

[Optimization] refactor(chat_handler,completion_handler): extract base classes and use AsyncLLM (#5195)

2025-12-25 16:28:15 +08:00

__init__.py

…

api_server.py

[Optimization] refactor(chat_handler,completion_handler): extract base classes and use AsyncLLM (#5195)

2025-12-25 16:28:15 +08:00

middleware.py

…

multi_api_server.py

[Feature] [PD Disaggregation] simplify configuration for pd-disaggregated deployment, and refactor post-init and usage for all ports (#5415)

2025-12-17 15:50:42 +08:00

protocol.py

[Optimization] refactor(chat_handler,completion_handler): extract base classes and use AsyncLLM (#5195)

2025-12-25 16:28:15 +08:00

response_processors.py

[Feature]Optimization of Thinking Pattern Framework (#4302)

2025-12-10 16:17:06 +08:00

run_batch.py

[Feature] [PD Disaggregation] simplify configuration for pd-disaggregated deployment, and refactor post-init and usage for all ports (#5415)

2025-12-17 15:50:42 +08:00

serving_chat.py

[APIServer][Feature] Add configurable worker health check timeout via FD_WORKER_ALIVE_TIMEOUT (#5865)

2026-01-05 09:47:12 +08:00

serving_completion.py

[BugFix] Fix redundant prompt_logprobs in the second chunk of streaming response when return_token_ids is enabled for v1/completions and fix trace file name (#5829)

2026-01-06 14:11:43 +08:00

serving_embedding.py

[Optimization] refactor(chat_handler,completion_handler): extract base classes and use AsyncLLM (#5195)

2025-12-25 16:28:15 +08:00

serving_engine.py

[Optimization] refactor(chat_handler,completion_handler): extract base classes and use AsyncLLM (#5195)

2025-12-25 16:28:15 +08:00

serving_models.py

…

serving_reward.py

[Optimization] refactor(chat_handler,completion_handler): extract base classes and use AsyncLLM (#5195)

2025-12-25 16:28:15 +08:00

test_openai.py

…

usage_calculator.py

…

utils.py

…