3D-MoE: Complementarity-Guided Hardware-Software Co-Design for MoE Decode on 3D-Stacked NMP

arXiv:2610.26991 · cs.AR, cs.AI, cs.DC · Submitted 2026-10-19 · Read on arXiv

cs.AR, cs.AI, cs.DC

Submitted: 2026-10-19

Updated: 2026-10-19

Terminology

Related papers