version: "3.3"
services:
  text-generation-webui:
    build:
      context: .
      args:
        # specify which cuda version your card supports: https://developer.nvidia.com/cuda-gpus
        TORCH_CUDA_ARCH_LIST: ${TORCH_CUDA_ARCH_LIST:-8.6;8.9+PTX}
        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:
      - ./user_data:/home/app/text-generation-webui/user_data
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]