Diagnosing FP4 inference: a layer-wise and block-wise sensitivity analysis of NVFP4 and MXFP4

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Cim, Musa, Topcu, Burak, Kandemir, Mahmut Taylan
Format:	Preprint
Published:	2026
Subjects:	Hardware Architecture Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2603.08747