version: '3'

services:
  llama-omni:
    build:
      context: .
      dockerfile: Dockerfile
    ports:
      - "7860:7860"
    volumes:
      - ./models:/app/models
    environment:
      - GRADIO_SERVER_NAME=0.0.0.0
      - GRADIO_SERVER_PORT=7860
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: 1
              capabilities: [gpu]