Skip to content

Inference: Bring chat completions API inline with vllm/official openAI spec - #5276

Merged
sidsingh-nvidia merged 5 commits into
NVIDIA:mainfrom
sidsingh-nvidia:siddharth/fix-think-token-retention-multi-turn
Jul 14, 2026
Merged

Inference: Bring chat completions API inline with vllm/official openAI spec#5276
sidsingh-nvidia merged 5 commits into
NVIDIA:mainfrom
sidsingh-nvidia:siddharth/fix-think-token-retention-multi-turn

flag for returning raw text optionally and lint

8f9657c
Select commit
Loading
Failed to load commit list.
DCO / DCO succeeded Jul 14, 2026 in 0s

DCO

Commit sign-off was manually approved.