Cache What Lasts: Token Retention for Memory-Bounded KV Cache in LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Bui, Ngoc, Sharma, Shubham, Lamba, Simran, Mishra, Saumitra, Ying, Rex
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2512.03324