FairyFuse: Multiplication-Free LLM Inference on CPUs via Fused Ternary Kernels

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zuo, Fei, Xi, Xiaoyan, Zeng, Quanyi, Wang, Feiyu, Leung, Ho Fai
Format:	Preprint
Published:	2026
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2604.20913