text-generation-webui/docker/nvidia/docker-compose.yml

version: "3.3"
services:
  text-generation-webui:
    build:
      context: .
      args:
        # Requirements file to use: 
        # | GPU | requirements file to use |
        # |--------|---------|
        # | NVIDIA | `requirements.txt` |
        # | AMD | `requirements_amd.txt` |
        # | CPU only | `requirements_cpu_only.txt` |
        # | Apple Intel | `requirements_apple_intel.txt` |
        # | Apple Silicon | `requirements_apple_silicon.txt` |
        # Default: requirements.txt`
        # BUILD_REQUIREMENTS: requirements.txt

        # Extension requirements to build: 
        # BUILD_EXTENSIONS: 

        # specify which cuda version your card supports: https://developer.nvidia.com/cuda-gpus
        TORCH_CUDA_ARCH_LIST: ${TORCH_CUDA_ARCH_LIST:-7.5} 
        BUILD_EXTENSIONS: ${BUILD_EXTENSIONS:-}
        APP_GID: ${APP_GID:-6972} 
        APP_UID: ${APP_UID-6972} 
    env_file: .env
    user: "${APP_RUNTIME_UID:-6972}:${APP_RUNTIME_GID:-6972}"
    ports:
      - "${HOST_PORT:-7860}:${CONTAINER_PORT:-7860}"
      - "${HOST_API_PORT:-5000}:${CONTAINER_API_PORT:-5000}"
    stdin_open: true
    tty: true
    volumes:
      - ./cache:/home/app/text-generation-webui/cache
      - ./characters:/home/app/text-generation-webui/characters
      - ./extensions:/home/app/text-generation-webui/extensions
      - ./loras:/home/app/text-generation-webui/loras
      - ./logs:/home/app/text-generation-webui/logs
      - ./models:/home/app/text-generation-webui/models
      - ./presets:/home/app/text-generation-webui/presets
      - ./prompts:/home/app/text-generation-webui/prompts
      - ./softprompts:/home/app/text-generation-webui/softprompts
      - ./training:/home/app/text-generation-webui/training
      - ./cloudflared:/etc/cloudflared
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]