LASP-2: Rethinking Sequence Parallelism for Linear Attention and Its Hybrid

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Sun, Weigao, Lan, Disen, Zhong, Yiran, Qu, Xiaoye, Cheng, Yu
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/2502.07563