services:
  vllm:
    image: vllm/vllm-openai:latest
    network_mode: "host"
    volumes:
      - $HOME/.cache/huggingface:/root/.cache/huggingface
    ports:
      - "8000:8000"
    devices:
      - nvidia.com/gpu=all
    environment:
      - CUDA_VISIBLE_DEVICES=0
    command: []
    deploy:
      resources:
        reservations:
          devices:
          - driver: nvidia
            # that's the closest analogue to --gpus; provide
            # an integer amount of devices or 'all'
            count: 1
            # Devices are reserved using a list of capabilities, making
            # capabilities the only required field. A device MUST
            # satisfy all the requested capabilities for a successful
            # reservation.
            capabilities: [gpu]
    runtime: nvidia
  llamastack:
    depends_on:
    - vllm
    image: llamastack/distribution-remote-vllm
    network_mode: "host"
    volumes:
      - ~/.llama:/root/.llama
      # Link to ollama run.yaml file
      - ./run.yaml:/root/llamastack-run-remote-vllm.yaml
    ports:
      - "5000:5000"
    # Hack: wait for vllm server to start before starting docker
    entrypoint: bash -c "sleep 60; python -m llama_stack.distribution.server.server --yaml_config /root/llamastack-run-remote-vllm.yaml"
    deploy:
      restart_policy:
        condition: on-failure
        delay: 3s
        max_attempts: 5
        window: 60s
volumes:
  vllm: