services:
  vllm:
    command:
      - >-
        exec vllm serve /root/.cache/huggingface/hub/models--nvidia--Qwen3.8-Flash-Next-NVFP4/snapshots/fc694b54fb0174e0913e6adf86691ef85a4ead47
        --served-model-name qwen3.8-flash-next
        --host 0.0.0.0 --port 8000
        --tensor-parallel-size 1
        --dtype bfloat16 --kv-cache-dtype auto
        --gpu-memory-utilization ${GPU_MEMORY_UTILIZATION:-0.80}
        --max-model-len 262144 --max-num-seqs ${MAX_NUM_SEQS:-4} --max-num-batched-tokens 2048
        --enable-chunked-prefill --no-enable-prefix-caching
        --speculative-config '{"method":"mtp","num_speculative_tokens":2}'
        --enforce-eager --no-enable-flashinfer-autotune
        --load-format safetensors
        --reasoning-parser qwen3 --tool-call-parser qwen3_xml --enable-auto-tool-choice
        --api-key "$$(cat /run/secrets/qwen_api_key)"