Slim attention: cut your context memory in half without loss -- K-cache is all you need for MHA

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Graef, Nils, Wasielewski, Andrew
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2503.05840