compose.yaml

services:
  mineru-sglang-server:
    image: mineru-sglang:latest
    container_name: mineru-sglang-server
    restart: always
    profiles: ["sglang-server"]
    ports:
      - 30000:30000
    environment:
      MINERU_MODEL_SOURCE: local
    entrypoint: mineru-sglang-server
    command:
      --host 0.0.0.0
      --port 30000
      # --enable-torch-compile  # You can also enable torch.compile to accelerate inference speed by approximately 15%
      # --dp-size 2  # If using multiple GPUs, increase throughput using sglang's multi-GPU parallel mode
      # --tp-size 2  # If you have more than one GPU, you can expand available VRAM using tensor parallelism (TP) mode.
      # --mem-fraction-static 0.5  # If running on a single GPU and encountering VRAM shortage, reduce the KV cache size by this parameter, if VRAM issues persist, try lowering it further to `0.4` or below.
    ulimits:
      memlock: -1
      stack: 67108864
    ipc: host
    healthcheck:
      test: ["CMD-SHELL", "curl -f http://localhost:30000/health || exit 1"]
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              device_ids: ["0"]
              capabilities: [gpu]

  mineru-api:
    image: mineru-sglang:latest
    container_name: mineru-api
    restart: always
    profiles: ["api"]
    ports:
      - 8000:8000
    environment:
      MINERU_MODEL_SOURCE: local
    entrypoint: mineru-api
    command:
      --host 0.0.0.0
      --port 8000
      # parameters for sglang-engine
      # --enable-torch-compile  # You can also enable torch.compile to accelerate inference speed by approximately 15%
      # --dp-size 2  # If using multiple GPUs, increase throughput using sglang's multi-GPU parallel mode
      # --tp-size 2  # If you have more than one GPU, you can expand available VRAM using tensor parallelism (TP) mode.
      # --mem-fraction-static 0.5  # If running on a single GPU and encountering VRAM shortage, reduce the KV cache size by this parameter, if VRAM issues persist, try lowering it further to `0.4` or below.
    ulimits:
      memlock: -1
      stack: 67108864
    ipc: host
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              device_ids: [ "0" ]
              capabilities: [ gpu ]

  mineru-gradio:
    image: mineru-sglang:latest
    container_name: mineru-gradio
    restart: always
    profiles: ["gradio"]
    ports:
      - 7860:7860
    environment:
      MINERU_MODEL_SOURCE: local
    entrypoint: mineru-gradio
    command:
      --server-name 0.0.0.0
      --server-port 7860
      --enable-sglang-engine true  # Enable the sglang engine for Gradio
      # --enable-api false  # If you want to disable the API, set this to false
      # --max-convert-pages 20  # If you want to limit the number of pages for conversion, set this to a specific number
      # parameters for sglang-engine
      # --enable-torch-compile  # You can also enable torch.compile to accelerate inference speed by approximately 15%
      # --dp-size 2  # If using multiple GPUs, increase throughput using sglang's multi-GPU parallel mode
      # --tp-size 2  # If you have more than one GPU, you can expand available VRAM using tensor parallelism (TP) mode.
      # --mem-fraction-static 0.5  # If running on a single GPU and encountering VRAM shortage, reduce the KV cache size by this parameter, if VRAM issues persist, try lowering it further to `0.4` or below.
    ulimits:
      memlock: -1
      stack: 67108864
    ipc: host
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              device_ids: [ "0" ]
              capabilities: [ gpu ]