Chat with Llama 3.2 Vision

Overview

Llama 3.2 Vision is Meta's multimodal open model capable of image reasoning, captioning, and visual QA. This project deploys it using LitServe for production-grade serving with minimal boilerplate.

Get Started

pip install -r requirements.txt
python server.py   # LitServe API on localhost:8000
python client.py   # send image + prompt