Expected Attention: KV Cache Compression by Estimating Attention from Future Queries Distribution

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Devoto, Alessio, Jeblick, Maximilian, Jégou, Simon
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence 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/2510.00636