sMoE: Elastic MoE-Based Inference with Serverless Computing via Fine-grained Expert Scaling

, , , , , ,

Venue: ACM/IEEE Design Automation Conference (DAC), 2026.

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.

Links: PDF Code