AdaFuse: Accelerating Dynamic Adapter Inference via Token-Level Pre-Gating and Fused Kernel Optimization

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Qiyang, Kong, Rui, Li, Yuchen, Cai, Hengyi, Wang, Shuaiqiang, Kong, Linghe, Chen, Guihai, Yin, Dawei
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2603.11873