services:
  vllm:
    build:
      context: .
      dockerfile: Dockerfile
    ports:
      - "8000:8000"
    environment:
      - OMP_NUM_THREADS=128
      - CUDA_LAUNCH_BLOCKING=0
      - PYTHONUNBUFFERED=1
      - VLLM_RPC_TIMEOUT_MS=600000
    command:
      - /model
      - --trust-remote-code
      - --enable-expert-parallel
      - --tensor-parallel-size=8
      - --enforce-eager
      #- --compilation-config
      #- '{"cudagraph_mode": "FULL_DECODE_ONLY", "custom_ops": ["all"], "cudagraph_capture_sizes": [1, 2, 4, 8], "max_cudagraph_capture_size": 8}'
      - --tokenizer-mode=deepseek_v4
      - --host=0.0.0.0
      - --port=8000
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
    volumes:
      - /root/nvidia-meeting/DeepSeek-V4-Pro-NVFP4:/model:ro