Characterizing and Optimizing LLM Inference Workloads on CPU-GPU Coupled Architectures

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Vellaisamy, Prabhu, Labonte, Thomas, Chakraborty, Sourav, Turner, Matt, Sury, Samantika, Shen, John Paul
Format:	Preprint
Published:	2025
Subjects:	Distributed, Parallel, and Cluster Computing Artificial Intelligence Hardware Architecture Performance
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2504.11750