AQUA: Attention via QUery mAgnitudes for Memory and Compute Efficient Inference in LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	S, Santhosh G, Prakash, Saurav, Ravindran, Balaraman
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/2509.11155