Is your feature request related to a problem? Please describe.

https://openai.com/open-models/

According to https://huggingface.co/openai/gpt-oss-120b, we need to use a pre-released version of vLLM so we might need to wait until the official release of 0.10.1.

uv pip install --pre vllm==0.10.1+gptoss \
    --extra-index-url https://wheels.vllm.ai/gpt-oss/ \
    --extra-index-url https://download.pytorch.org/whl/nightly/cu128 \
    --index-strategy unsafe-best-match

vllm serve openai/gpt-oss-120b

Describe the solution you'd like

Describe alternatives you've considered

Additional context