Intrinsic Structure as a Proxy for Saliency: SVD-Based Weight Preservation for Mixed-Precision Quantization in Large Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Landge, Shashank, Patil, Abhishek, kamble, Tejas, Buddhivant, Bhushan, Joshi, Priyanka
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/2512.01343