GRKV: Global Regression for Training-Free KV Cache Compression in Long-Context LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Peng, Junjie, Wu, You, Wu, Haoyi, Han, Jialong, Xie, Xiaohua, Tu, Kewei, Lai, Jianhuang
Format:	Preprint
Published:	2026
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2605.31105