Add Vlm Model

Add support for a new Vision-Language Model (VLM) to AutoRound, including multimodal block handler, calibration dataset template, and special model handling. Use when integrating a new VLM like LLaVA, Qwen2-VL, GLM-Image, Phi-Vision, or similar multi-modal models for quantization.

intel Updated 122 repo stars
AutoRound Overview

File contents

intel/auto-round commit 7b26fc9fad

Frequently asked questions

npx get-skill add intel/add-vlm-model