"Pre-gated MoE: An Algorithm-System Co-Design for Fast and Scalable ..."

Ranggi Hwang et al. (2024)

> Home

Details and statistics

DOI: 10.1109/ISCA59077.2024.00078

access: closed

type: Conference or Workshop Paper

metadata version: 2024-10-18

- view
  - electronic edition via DOI
  - unpaywalled version
  authority control:
- export record
  dblp key:
  - conf/isca/HwangWCHTCY24
- ask others
- share record
  persistent URL:
  - https://dblp.org/rec/conf/isca/HwangWCHTCY24
Ranggi Hwang, Jianyu Wei, Shijie Cao, Changho Hwang, Xiaohu Tang, Ting Cao, Mao Yang:
Pre-gated MoE: An Algorithm-System Co-Design for Fast and Scalable Mixture-of-Expert Inference. ISCA 2024: 1018-1031

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.