AhaKV: Adaptive Holistic Attention-Driven KV Cache Eviction for Efficient Inference of Large Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Gu, Yifeng, Jiang, Zicong, Jin, Jianxiu, Guo, Kailing, Zhang, Ziyang, Xu, Xiangmin
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2506.03762