AdapMoE: Adaptive Sensitivity-based Expert Gating and Management for Efficient MoE Inference

Shuzhang Zhong, Ling Liang, Yuan Wang, Runsheng Wang, Ru Huang, Meng Li
October, 2024
Type
Conference paper
Publication
In ACM/IEEE International Conference on Computer Aided Design (ICCAD) 2024
Shuzhang Zhong
Shuzhang Zhong
Second-Year PhD student

My research interests include distributed robotics, mobile computing and programmable matter.