docker-compose.yml

services:
  vllm:
    image: vllm/vllm-openai:latest
    container_name: vllm
    restart: unless-stopped
    ipc: host
    shm_size: 32gb
    ports:
      - "8080:8000"
    volumes:
      - hf-cache:/root/.cache/huggingface
      - vllm-cache:/root/.cache/vllm
    environment:
      VLLM_ALLOW_LONG_MAX_MODEL_LEN: "1"
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              device_ids: ['0', '1']
              capabilities: [gpu]
    command: cyankiwi/Qwen3.6-27B-AWQ-BF16-INT4 --tensor-parallel-size 2 --max-model-len 262144 --gpu-memory-utilization 0.93 --mm-encoder-tp-mode data --kv-cache-dtype fp8 --enable-prefix-caching --enable-chunked-prefill --max-num-batched-tokens 4096 --reasoning-parser qwen3 --tool-call-parser qwen3_coder --enable-auto-tool-choice --max-num-seqs 2 --speculative-config '{"method":"mtp","num_speculative_tokens":2}' --performance-mode interactivity

volumes:
  hf-cache:
    name: hf-cache
  vllm-cache:
    name: vllm-cache