services:
  magicquill:
    build:
      context: .
      dockerfile: Dockerfile
    environment:
      #
      # Set environment variables for your container
      #
      # expandable_segments (default False) allows the allocator to create a segment initially and then expand its size later when more memory is needed.
      # Ref: https://pytorch.org/docs/stable/notes/cuda.html
      PYTORCH_CUDA_ALLOC_CONF: "expandable_segments:False"
    runtime: nvidia  # Use NVIDIA runtime for GPU support
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: 1
              capabilities: ["gpu"]
    volumes:
      - /data/magicquill/models:/home/quill/MagicQuill/models
    ports:
      - "7860:7860"  # Map container port to host port if applicable