Head-Aware KV Cache Compression for Efficient Visual Autoregressive Modeling

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Qin, Ziran, Lv, Youru, Lin, Mingbao, Guo, Hang, Zhang, Zeren, Zou, Danping, Lin, Weiyao
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2504.09261