"MoE-Lightning: High-Throughput MoE Inference on Memory-constrained GPUs."

Shiyi Cao et al. (2025)

> Home

Details and statistics

DOI: 10.1145/3669940.3707267

access: closed

type: Conference or Workshop Paper

metadata version: 2025-03-07

- view
  - electronic edition via DOI
  - unpaywalled version
  authority control:
- export record
  dblp key:
  - conf/asplos/CaoLGSL0GZS25
- ask others
- share record
  persistent URL:
  - https://dblp.org/rec/conf/asplos/CaoLGSL0GZS25
Shiyi Cao, Shu Liu, Tyler Griggs, Peter Schafhalter, Xiaoxuan Liu, Ying Sheng, Joseph E. Gonzalez, Matei Zaharia, Ion Stoica:
MoE-Lightning: High-Throughput MoE Inference on Memory-constrained GPUs. ASPLOS (1) 2025: 715-730

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.