MoE-nD: Per-Layer Mixture-of-Experts Routing for Multi-Axis KV Cache Compression

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sun, Libo, He, Peixiong, Harn, Po-Wei, Qin, Xiao
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!