services:
  vllm:
    image: vllm/vllm-openai:latest
    container_name: vllm
    profiles:
      - vllm
    restart: unless-stopped
    ipc: host
    ports:
      - "${VLLM_PORT:-8000}:8000"
    environment:
      - HF_TOKEN=${HF_TOKEN:-}
      - CUDA_VISIBLE_DEVICES=0
      - VLLM_MODEL=${VLLM_MODEL}
      - SERVED_MODEL_NAME=${SERVED_MODEL_NAME:-qwen3.6-27b}
      - MAX_MODEL_LEN=${MAX_MODEL_LEN:-131072}
      - MAX_NUM_SEQS=${MAX_NUM_SEQS:-1}
      - GPU_MEMORY_UTILIZATION=${GPU_MEMORY_UTILIZATION:-0.95}
      - KV_CACHE_DTYPE=${KV_CACHE_DTYPE:-fp8}
      - QUANTIZATION=${QUANTIZATION:-}
      - VLLM_EXTRA_ARGS=${VLLM_EXTRA_ARGS:---language-model-only --enforce-eager --reasoning-parser qwen3}
    volumes:
      - ${DATA_ROOT:-/data}/apps/vllm/huggingface:/root/.cache/huggingface
      - ./scripts/vllm-entrypoint.sh:/usr/local/bin/vllm-entrypoint.sh:ro
    gpus: all
    entrypoint: ["/bin/bash", "/usr/local/bin/vllm-entrypoint.sh"]