services:
  vllm:
    image: atl.vultrcr.com/vllm/vllm-with-lmcache:dream-build
    pull_policy: always
    entrypoint:
      - bash
      - -c
      - |
        python3 /patches/patch_vllm_weights.py
        exec vllm serve "$$@"
      - --
    environment:
      - HF_TOKEN=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
    command:
      - /model
      - --trust-remote-code
      - --kv-cache-dtype=fp8
      - --block-size=256
      - --enable-expert-parallel
      - --tensor-parallel-size=8
      - --compilation-config={"cudagraph_mode":"FULL_AND_PIECEWISE","custom_ops":["all"]}
      - --attention_config.use_fp4_indexer_cache=True
      - --moe-backend=deep_gemm_mega_moe
      - --tokenizer-mode=deepseek_v4
      - --tool-call-parser=deepseek_v4
      - --enable-auto-tool-choice
      - --reasoning-parser=deepseek_v4
      - --speculative_config={"method":"mtp","num_speculative_tokens":2}
      - --host=0.0.0.0
      - --port=8000
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
    ipc: host
    security_opt:
      - seccomp:unconfined
    tty: true
    stdin_open: true
    volumes:
      - /root/nvidia-meeting/DeepSeek-V4-Pro-NVFP4:/model:ro
      - /root/nvidia-meeting/deepseek-v4-quant/patches:/patches:ro
    network_mode: host