Tiled Flash Linear Attention: More Efficient Linear RNN and xLSTM Kernels

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Beck, Maximilian, Pöppel, Korbinian, Lippe, Phillip, Hochreiter, Sepp
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2503.14376