IndexCache: Accelerating Sparse Attention via Cross-Layer Index Reuse

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Bai, Yushi, Dong, Qian, Jiang, Ting, Lv, Xin, Du, Zhengxiao, Zeng, Aohan, Tang, Jie, Li, Juanzi
Format:	Preprint
Published:	2026
Subjects:	Computation and Language Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2603.12201