Adapt New LLM

Adapt AutoRound to support a new LLM architecture that doesn't work out-of-the-box. Use when quantization fails for a new model type, block detection doesn't find layers, MoE models need unfusing, custom forward passes are needed, or non-standard linear layer types need handling.

intel Updated 122 repo stars
AutoRound Overview

File contents

intel/auto-round commit 782771158f

Frequently asked questions

npx get-skill add intel/adapt-new-llm