DOTA: detect and omit weak attentions for scalable transformer acceleration.

Zheng Qu Liu Liu Fengbin Tu Zhaodong Chen Yufei Ding Yuan Xie

Published in: ASPLOS (2022)

Keyphrases

detection algorithm
highly scalable
machine learning
lightweight
detection method
power system
automatic detection
fault diagnosis
information retrieval
artificial intelligence
decision making
fuzzy logic
web scale