RaaS: Reasoning-Aware Attention Sparsity for Efficient LLM Reasoning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Hu, Junhao, Huang, Wenrui, Wang, Weidong, Li, Zhenwen, Hu, Tiancheng, Liu, Zhixia, Chen, Xusheng, Xie, Tao, Shan, Yizhou
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/2502.11147