The $qs$ Inequality: Quantifying the Double Penalty of Mixture-of-Experts at Inference

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Adhinarayanan, Vignesh, Jayasena, Nuwan
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Hardware Architecture Distributed, Parallel, and Cluster Computing Performance 68T07, 68M20 I.2.6; C.4; C.1.2
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2603.08960