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

Zheng Qu et al. (2022)

> Home

Details and statistics

DOI: 10.1145/3503222.3507738

access: closed

type: Conference or Workshop Paper

metadata version: 2022-12-05

- view
  - electronic edition via DOI
  - unpaywalled version
  authority control:
- export record
  dblp key:
  - conf/asplos/Qu0TCD022
- ask others
- share record
  persistent URL:
  - https://dblp.org/rec/conf/asplos/Qu0TCD022
Zheng Qu, Liu Liu, Fengbin Tu, Zhaodong Chen, Yufei Ding, Yuan Xie:
DOTA: detect and omit weak attentions for scalable transformer acceleration. ASPLOS 2022: 14-26

manage site settings

To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.