Model Tells You Where to Merge: Adaptive KV Cache Merging for LLMs on Long-Context Tasks

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Zheng, Jin, Boxiao, Yu, Zhongzhi, Zhang, Minjia
Format:	Preprint
Published:	2024
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/2407.08454