Chat with Qwen2-VL

Overview

Qwen2-VL is Alibaba Cloud's flagship multimodal LLM series, supporting image understanding, multi-image reasoning, and video analysis.

This project provides a production-ready deployment using LitServe for high-throughput inference, with a clean chat interface for visual question answering.

Get Started

pip install -r requirements.txt
python server.py   # starts LitServe inference API
python client.py   # send image + text queries