Value-and-Structure Alignment for Routing-Consistent Quantization of Mixture-of-Experts Models

arXiv:2606.05688v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) models scale foundation models efficiently by activating only a subset of experts for each token, but their large number of expert parameters still makes quantization essential for practical deployment. Unlike dense models, however, MoE models are sensitive to routing...

Læs hele artiklen hos kilden.