#!/usr/bin/env bash
set -euo pipefail

docker.m.daocloud.io/vllm/vllm-openai:latest \
  /model \
  --trust-remote-code --dtype bfloat16 --tensor-parallel-size 1 \
  --enable-auto-tool-choice --tool-call-parser qwen3_xml --reasoning-parser qwen3 \
  --max-model-len 65536 --gpu-memory-utilization 0.75 --max-num-seqs 8 \
  --served-model-name qwen3.6-27b --enable-prefix-caching --host 0.0.0.0 --port 8000