PagedMoE: Cross-Precision Expert Caching for Token-Level Dynamic Precision in SSD-Resident MoE Inference

arXiv:2611.03173 · cs.AR · Submitted 2026-11-02 · Read on arXiv

cs.AR

Submitted: 2026-11-02

Updated: 2026-11-02

Comments: 13 pages, 10 figures, 2 tables

Code: https://github.com/ikawrakow/ik_

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

Sources

Related papers