FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lai, Xunhao, Lu, Jianqiao, Luo, Yao, Ma, Yiyuan, Zhou, Xun
Format:	Preprint
Published:	2025
Subjects:	Machine Learning 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/2502.20766