Flora Feng 6f65fde419 [Bugfix][Frontend] Apply Harmony adjust_request in batched chat completions (#58958) ...

Signed-off-by: sfeng33 <4florafeng@gmail.com>

2026-09-28 04:12:04 +00:00

..

__init__.py

[Refactor] [6/N] to simplify the vLLM openai chat_completion serving architecture (#32240)

2026-01-13 13:01:39 +00:00

api_router.py

[Frontend][last/N] Move all non-OpenAI content out of the OpenAI folder. (#56369)

2026-09-11 05:33:26 +00:00

batch_serving.py

[Bugfix][Frontend] Apply Harmony adjust_request in batched chat completions (#58958)

2026-09-28 04:12:04 +00:00

protocol.py

fix(config): apply presence_penalty/frequency_penalty from override-generation-config (#50769)

2026-09-24 08:48:18 -07:00

serving.py

[Bugfix][Frontend] Use a fresh parser per choice in non-streaming chat completions (#58939)

2026-09-28 02:01:35 +00:00