EliteKV: Scalable KV Cache Compression via RoPE Frequency Selection and Joint Low-Rank Projection

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhou, Yuhao, Song, Sirui, Liu, Boyang, Xi, Zhiheng, Jin, Senjie, Fan, Xiaoran, Zhang, Zhihao, Li, Wei, Huang, Xuanjing
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence 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/2503.01586