Guess-Verify-Refine: Data-Aware Top-K for Sparse-Attention Decoding on Blackwell via Temporal Correlation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Cheng, Long, Zhao, Ritchie, Liu, Timmy, Li, Mindy, Qiao, Xianjie, Duan, Kefeng, Chen, Yu-Jung, Chen, Xiaoming, Rouhani, Bita Darvish, Yang, June
Format:	Preprint
Published:	2026
Subjects:	Distributed, Parallel, and Cluster Computing Hardware Architecture Performance 68W10 C.1.4; D.1.3; C.5
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2604.22312