services:
  llamastack:
    image: distribution-nvidia:dev
    network_mode: "host"
    volumes:
      - ~/.llama:/root/.llama
      - ./run.yaml:/root/llamastack-run-nvidia.yaml
    ports:
      - "8321:8321"
    environment:
      - INFERENCE_MODEL=${INFERENCE_MODEL:-Llama3.1-8B-Instruct}
      - NVIDIA_API_KEY=${NVIDIA_API_KEY:-}
    entrypoint: bash -c "python -m llama_stack.distribution.server.server --yaml-config /root/llamastack-run-nvidia.yaml"
    deploy:
      restart_policy:
        condition: on-failure
        delay: 3s
        max_attempts: 5
        window: 60s