#!/bin/bash
# Start vLLM server with OpenAI-compatible API
# This uses vLLM's built-in server which properly handles streaming

vllm serve Qwen/Qwen2.5-7B-Instruct \
  --host 0.0.0.0 \
  --port 9000 \
  --tensor-parallel-size 1 \
  --gpu-memory-utilization 0.85 \
  --max-model-len 4096 \
  --download-dir /workspace/huggingface_cache \
  --trust-remote-code