concurrency: 1
command:
    - python3
    - -m
    - vllm.entrypoints.openai.api_server
    - --model
    - /model
    - --served-model-name
    - llm
    - --max-model-len
    - '256000'
    - --gpu-memory-utilization
    - '0.95'
    - --trust-remote-code
    - -tp
    - '4'
    - --max-num-seqs
    - '2'
    - --disable-log-requests
    - --disable-frontend-multiprocessing
    - --max-num-batched-tokens
    - '4096'
    - --enable-chunked-prefill
    - --max-seq-len-to-capture
    - '32768'
    - --enforce-eager
    - --enable-auto-tool-choice
    - --tool-call-parser
    - qwen3_coder
    - --reasoning-parser
    - qwen3
    - --enable-prefix-caching
    - --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
    - name: VLLM_COREX_FA2_LIBRARY
      value: /usr/local/corex/lib64/libcorex_fa2.so
    - name: VLLM_COREX_GDN_LIBRARY
      value: /usr/local/corex/lib64/libcorex_gdn.so
    - name: VLLM_COREX_MOE_LIBRARY
      value: /usr/local/corex/lib64/libcorex_moe.so
    - name: VLLM_REQUEST_METRICS_FILE
      value: /tmp/vllm-request-metrics.jsonl
    - name: VLLM_CACHE_BLOCK_SIZE
      value: '16'