VLLM example working docker compose with nginx

docker-compose.yml

version: '3.8'

services:
  vllm:
    image: vllm/vllm-openai:latest
    container_name: deepseek-coder-vllm
    restart: unless-stopped
    expose:
      - "8000"
    volumes:
      - /root/.cache/huggingface:/root/.cache/huggingface
    environment:
      - CUDA_VISIBLE_DEVICES=0
      - PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: 1
              capabilities: [gpu]
    command: >
      --model deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct
      --port 8000
      --host 0.0.0.0
      --trust-remote-code
      --tensor-parallel-size 1
      --gpu-memory-utilization 0.85
      --max-model-len 16384
      --disable-log-requests
      --enable-auto-tool-choice
      --tool-call-parser hermes
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8000/health"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 300s

  nginx:
    image: nginx:alpine
    container_name: deepseek-coder-nginx
    restart: unless-stopped
    ports:
      - "80:80"
    volumes:
      - ./nginx.conf:/etc/nginx/nginx.conf:ro
    depends_on:
      vllm:
        condition: service_healthy
    healthcheck:
      test: ["CMD", "wget", "--quiet", "--tries=1", "--spider", "http://localhost/health"]
      interval: 30s
      timeout: 10s
      retries: 3