llm_vector_server/docker-compose.yaml

services:
  vllm-qwen:
    image: vllm-qwen
    container_name: vllm-qwen
    ports:
      - "8000:8000"
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
    restart: always