Monic: In-network mixture-of-experts inference on programmable data planes

In-network inference has emerged as a promising paradigm for enabling intelligent packet processing at the line rate within programmable data planes. However, it is fundamentally limited by an inherent conflict between model accuracy and the resource constraints of programmable data planes. This for...

Full description

Bibliographic Details

Main Authors:	Xiaoquan Zhang, Bowen Liang, Fung Po Tso, Yuhui Deng, Zhen Zhang, Kaimin Wei, Weijia Jia, Lin Cui
Format:	Default Conference proceeding
Published:	2026
Subjects:	P4 in-network inference programmable data plane decision trees mixture of experts
Online Access:	https://hdl.handle.net/2134/31035229.v1
Tags:	Add Tag No Tags, Be the first to tag this record!