WeightedKV: Attention Scores Weighted Key-Value Cache Merging for Large Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yuan, Jian, He, Ziwei, Bai, Haoli, Leng, Jingwen, Jiang, Bo
Format:	Preprint
Published:	2025
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/2503.01330