The Local LLM Index / Quantization & Formats / #157

AutoGPTQ/AutoGPTQ

by AutoGPTQ · Quantization & Formats · updated 1y ago

An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.

42
momentum
5,076
stars
541
forks
#157
rank
deep-learninginferencelarge-language-modelsllmsnlppytorchquantizationtransformertransformers
View on GitHub →