concurrency: 1
command:
    - python3
    - -m
    - vllm.entrypoints.openai.api_server
    - --model
    - /model
    - --served-model-name
    - llm
    - --max-model-len
    - '80000'
    - --gpu-memory-utilization
    - '0.95'
    - --trust-remote-code
    - -tp
    - '4'
    - --max-num-seqs
    - '2'
    - --max-num-batched-tokens
    - '4096'
    - --enable-chunked-prefill
    - --disable-log-requests
    - --disable-frontend-multiprocessing
    - --enforce-eager
    - --enable-auto-tool-choice
    - --tool-call-parser
    - qwen3_coder
    - --reasoning-parser
    - qwen3
    - --enable-prefix-caching
    - --max-seq-len-to-capture
    - '8192'
    - --dtype
    - half
env:
    - name: VLLM_ENGINE_ITERATION_TIMEOUT_S
      value: '3600'
    - name: VLLM_ATTENTION_BACKEND
      value: XFORMERS
    - name: ENABLE_CUSTOM_IPC
      value: '1'
    - name: PYTHONPATH
      value: /usr/local/corex/lib/python3/dist-packages:/usr/local/corex/lib64/python3/dist-packages
    - name: LD_LIBRARY_PATH
      value: /usr/local/corex/lib64:/usr/local/openmpi/lib:/usr/local/corex/lib64/python3/dist-packages/ixformer
    - name: PYTORCH_CUDA_ALLOC_CONF
      value: max_split_size_mb:512
    - name: OMP_NUM_THREADS
      value: '1'
    - name: BI100_MOE_COREX_DIRECT_ROUTED
      value: '1'
    - name: BI100_GDN_COREX_PACKED_DECODE
      value: '1'