NLPExplorer
Papers
Venues
Authors
Authors Timeline
Field of Study
URLs
ACL N-gram Stats
TweeNLP
API
Team
HookMoE: A learnable performance compensation strategy of Mixture-of-Experts for LLM inference acceleration
Cheng Longkai
|
Along He
|
Mulin Li
|
Xie Xueshuo
|
Tao Li
|
Paper Details:
Month: November
Year: 2025
Location: Suzhou, China
Venue:
EMNLP |
Citations
URL
No Citations Yet
https://github.com/KerwinKai/HookMoE
https://docs.nvidia
https://mlsys.wuklab.io/posts/
Field Of Study