Thin Keys, Full Values: Reducing KV Cache via Low-Dimensional Attention Selection

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yao, Hengshuai, Chen, Xing, Murtadha, Ahmed, Wang, Guan
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2603.04427