linzm1007andmergify[bot] <37929162+mergify[bot]@users.noreply.github.com> 739af5c7e1 [Reasoning] [Bugfix] Reject invalid thinking_token_budget values (#43402) ...

Signed-off-by: linzm1007 <linzm1007@126.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>

2026-05-26 03:37:30 -07:00

..

__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

Add /v1/chat/completions/batch endpoint for batched chat completions (#38011)

2026-03-26 12:13:33 +08:00

batch_serving.py

[ROCm][CI] Stabilize 400 error return code for invalid schema inputs (#43016)

2026-05-24 10:06:49 +00:00

protocol.py

[Reasoning] [Bugfix] Reject invalid thinking_token_budget values (#43402)

2026-05-26 03:37:30 -07:00

serving.py

[R3] Add routed experts to openai entrypoint (#38939)

2026-05-20 09:07:59 -07:00

stream_harmony.py

[Bugfix] Handle real-world gpt-oss tool call output in Harmony parsing (#42454)

2026-05-13 17:54:46 +00:00