text-generation-webui/docs/ExLlama.md
2023-06-16 20:35:38 -03:00

465 B

ExLlama

About

ExLlama is an extremely optimized GPTQ backend for LLaMA models. It features much lower VRAM usage and much higher speeds due to not relying on unoptimized transformers code.

Installation:

  1. Clone the ExLlama repository into your repositories folder:
cd repositories
git clone https://github.com/turboderp/exllama
  1. Follow the remaining set up instructions in the official README: https://github.com/turboderp/exllama#exllama