services:
  inference:
    build:
      context: .
      dockerfile: Dockerfile
    image: rocm-vllm-inference:latest
    container_name: rocm-vllm-inference
    ports:
      - "8000:8000"
    env_file:
      - .env
    devices:
      - /dev/kfd
      - /dev/dri
    group_add:
      - video
      - render
    ipc: host
    shm_size: 16g
    cap_add:
      - SYS_PTRACE
    security_opt:
      - seccomp=unconfined
    restart: unless-stopped