services:
  vllm:
    build:
      context: .
      dockerfile: Dockerfile
      pull: false
    image: vllm-openai-rocm:nightly
    container_name: vllm-openai-rocm
    entrypoint: ["python"]
    command: ["-m", "app.start_openai"]
    ports:
      - "8001:8001"
    volumes:
      - /opt/model:/opt/model:ro
      - ./config.json:/workspace/config.json:ro
    environment:
      HF_HOME: /opt/model
      # 严格离线模式，禁止任何网络下载
      HF_HUB_OFFLINE: "1"
      TRANSFORMERS_OFFLINE: "1"
      HF_DATASETS_OFFLINE: "1"
      VLLM_ROCM_USE_AITER: "1"  # 打开总开关
      # 明确禁用不稳定的MoE后端，让其他AITER优化（如MHA）生效
      VLLM_ROCM_USE_AITER_MOE: "0"
      VLLM_ROCM_MOE_BACKEND: "TRITON"  # 强制MoE使用Triton
    devices:
      - /dev/kfd
      - /dev/dri
    group_add:
      - video
    ipc: host
    shm_size: 32g
    cap_add:
      - SYS_PTRACE
    security_opt:
      - seccomp=unconfined
    restart: unless-stopped