source/PaddleOCR/deploy/paddleocr_vl_docker/accelerators/nvidia-gpu/compose.yaml

services:
  paddleocr-vl-api:
    image: ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlepaddle/paddleocr-vl:${API_IMAGE_TAG_SUFFIX}
    container_name: paddleocr-vl-api
    ports:
      - 8080:8080
    depends_on:
      paddleocr-vlm-server:
        condition: service_healthy
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              device_ids: ["0"]
              capabilities: [gpu]
    shm_size: 64g
    # TODO: Allow using a regular user
    user: root
    restart: unless-stopped
    environment:
      - VLM_BACKEND=${VLM_BACKEND:-vllm}
    command: /bin/bash -c "paddlex --serve --pipeline /home/paddleocr/pipeline_config_${VLM_BACKEND}.yaml"
    healthcheck:
      test: ["CMD-SHELL", "curl -f http://localhost:8080/health || exit 1"]

  paddleocr-vlm-server:
    image: ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlepaddle/paddleocr-genai-${VLM_BACKEND}-server:${VLM_IMAGE_TAG_SUFFIX}
    container_name: paddleocr-vlm-server
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              device_ids: ["0"]
              capabilities: [gpu]
    shm_size: 64g
    # TODO: Allow using a regular user
    user: root
    restart: unless-stopped
    healthcheck:
      test: ["CMD-SHELL", "curl -f http://localhost:8080/health || exit 1"]
      start_period: 300s