concurrency: 1
command:
    - bash
    - -c
    - >-
        python3 /workspace/qwen3_6_scripts/patch_chat_template.py /model 2>&1 || echo '[runtime] chat template patch failed';
        exec python3 -m vllm.entrypoints.openai.api_server
        --model /model
        --served-model-name llm
        --max-model-len 131072
        --gpu-memory-utilization 0.92
        --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
        --enable-auto-tool-choice
        --tool-call-parser qwen3_coder
        --reasoning-parser qwen3
        --enable-prefix-caching
        --enforce-eager
        --dtype half
env:
    - name: VLLM_ENGINE_ITERATION_TIMEOUT_S
      value: '3600'
    - name: BI100_MAX_NUM_SEQS
      value: '2'
    # --- MoE kernel selection ---
    - name: BI100_MOE_COREX_DIRECT_ROUTED
      value: '1'
    - name: BI100_MOE_COREX_TOPK_SOFTMAX
      value: '1'
    # --- GDN kernel selection ---
    - name: BI100_GDN_COREX_PACKED_DECODE
      value: '1'
    # --- Hybrid KV/GDN cache ---
    - name: BI100_HYBRID_KV_ACCOUNTING
      value: full_attention
    - name: BI100_GDN_CACHE_POLICY
      value: admission64
    - name: BI100_GDN_RESTORE_MODE
      value: hybrid64
    # --- Image fetch timeout (container network) ---
    - name: VLLM_IMAGE_FETCH_TIMEOUT
      value: '10'