gpt-oss-puzzle-88B

docker run --gpus all -p 8000:8000 \
  --entrypoint bash \
  vllm/vllm-openai:v0.17.1 \
  -c "
    apt-get update && apt-get install -y git &&
    VLLM_PRECOMPILED_WHEEL_LOCATION=https://wheels.vllm.ai/1ac2ef2e5335ca0af99aee438998c9305461f563/vllm-0.18.1rc1.dev127%2Bg1ac2ef2e5-cp38-abi3-manylinux_2_31_$(uname -m).whl VLLM_USE_PRECOMPILED=1 pip install --no-build-isolation 'git+https://github.com/vllm-project/vllm.git@refs/pull/38135/head' &&
    pip install flashinfer-cubin==0.6.6 flashinfer-jit-cache==0.6.6 --extra-index-url https://flashinfer.ai/whl/cu129 &&
    export PYTORCH_ALLOC_CONF=expandable_segments:True &&
    vllm serve nvidia/gpt-oss-puzzle-88B \
      -tp 1 \
      --trust-remote-code \
      --kv-cache-dtype fp8 \
      --max-num-batched-tokens 8192 \
      --stream-interval 20 \
      --gpu-memory-utilization 0.95 \
      --max-num-seqs 8 \
      --max-cudagraph-capture-size 8 \
      --max-model-len 131072
  "