MicroMix: Efficient Mixed-Precision Quantization with Microscaling Formats for Large Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liu, Wenyuan, Meng, Haoqian, Luo, Yilun, Zhao, Yafei, Zhang, Peng, Ma, Xindian
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2508.02343