Publication

Enabling Efficient Low-bit Quantization based on Matrix Product Operators for KV Cache Compression

返回学术发表
Enabling Efficient Low-bit Quantization based on Matrix Product Operators for KV Cache Compression 论文配图

Jia-Qi Wang, Xiao-Qi Han, Peng-Jie Guo, Rong-Qiang He, Ze-Feng Gao#, Zhong-Yi Lu#

Neural Networks, 108467., 2025

摘要

In this work, we introduce MPOQ, a novel data-free quantization technique based on matrix product operators (MPO) to effectively compress the KV cache.