services:
  firered-ocr:
    image: vllm/vllm-openai@sha256:2296a2a7e1ce1dc59c6577ba5900f4e9910b76c4a0cb134833a8137f92404dfa
    pull_policy: never
    container_name: firered-ocr
    restart: unless-stopped
    entrypoint: ["/bin/sh", "-c"]
    command:
      - >-
        pip install qwen-vl-utils -q &&
        vllm serve /models/firered-ocr
        --served-model-name firered-ocr
        --load-format safetensors
        --trust-remote-code
        --dtype half
        --gpu-memory-utilization 0.30
        --max-num-seqs 1
        --max-model-len 4096
        --enforce-eager
        --host 0.0.0.0
        --port 8001
    environment:
      NVIDIA_VISIBLE_DEVICES: "1"
      CUDA_VISIBLE_DEVICES: "0"
      NVIDIA_DRIVER_CAPABILITIES: compute,utility
    ports:
      - "8001:8001"
    volumes:
      - /mnt/cache-appdata/firered-ocr:/models/firered-ocr
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              device_ids: ["1"]
              capabilities: [gpu]
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8001/health"]
      interval: 30s
      timeout: 10s
      start_period: 90s
      retries: 3
    labels:
      com.getarcaneapp.arcane.icon: firered-ocr
      net.unraid.docker.icon: https://github.com/FireRedTeam.png?size=128
      net.unraid.docker.webui: http://[IP]:[PORT:8001]/docs