Giters

lpyhdzx / DecoQuant_code

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Unlocking Data-free Low-bit Quantization with Matrix Decomposition for KV Cache Compression

This is the implementation of the paper:

Peiyu Liu, Ze-Feng Gao, Wayne Xin Zhao, Yipeng Ma, Tao Wang and Ji-Rong Wen. Unlocking Data-free Low-bit Quantization with Matrix Decomposition for KV Cache Compression Updates:

  • [May 21] We update the README.

Code for paper

Code is coming soon!

About