Reducing Compute Waste in LLMs through Kernel-Level DVFS

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Spaan, Jeffrey, Chen, Kuan-Hsun, Varbanescu, Ana-Lucia
Format:	Preprint
Published:	2026
Subjects:	Performance Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2601.08539