PAPI: Exploiting Dynamic Parallelism in Large Language Model Decoding with a Processing-In-Memory-Enabled Computing System

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	He, Yintao, Mao, Haiyu, Giannoula, Christina, Sadrosadati, Mohammad, Gómez-Luna, Juan, Li, Huawei, Li, Xiaowei, Wang, Ying, Mutlu, Onur
Format:	Preprint
Published:	2025
Subjects:	Hardware Architecture Artificial Intelligence Distributed, Parallel, and Cluster Computing Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2502.15470