sMoE: Elastic MoE-Based Inference with Serverless Computing via Fine-grained Expert Scaling
Xiaofei Yue
,
Ziming Zhao
,
Jiongchi Yu
,
Huidong Ma
,
Zhaoxuan Li
,
Tingting Li
,
Jianwei Yin
Venue: ACM/IEEE Design Automation Conference (DAC), 2026.
PDF
ยท Code
sMoE: Elastic MoE-Based Inference with Serverless Computing via Fine-grained Expert Scaling
Authors: Xiaofei Yue, Ziming Zhao, Jiongchi Yu, Huidong Ma, Zhaoxuan Li, Tingting Li, Jianwei Yin
Venue: ACM/IEEE Design Automation Conference (DAC), 2026.