The Local LLM Index / Quantization & Formats / #149
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
5,067
stars
543
forks
#149
rank
deep-learninginferencelarge-language-modelsllmsnlppytorchquantizationtransformertransformers
View on GitHub →