EdgeATP: An adaptive tensor parallelism framework for scalable and efficient transformer inference on edge clusters
Journal of Systems Architecture · 2026-08 · 177 · 103861
DOI: 10.1016/j.sysarc.2026.103861 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Systems Architecture, 2026-08. Verfasst von Wanqi Wang und 4 weiteren Autor:innen. Die Arbeit nennt 53 Literaturangaben. Gefördert von: Beijing Natural Science Foundation, National Natural Science Foundation of China.
Abstract (Originalsprache)
Kein Abstract verfügbar.
Förderung
- Beijing Natural Science Foundation
- National Natural Science Foundation of China
Zitieren
APA
Wang, W., Jing, B., He, S., Song, Z., & Fang, W. (2026). EdgeATP: An adaptive tensor parallelism framework for scalable and efficient transformer inference on edge clusters. Journal of Systems Architecture, 177, 103861. https://doi.org/10.1016/j.sysarc.2026.103861
Vancouver
Wang W, Jing B, He S, Song Z, Fang W. EdgeATP: An adaptive tensor parallelism framework for scalable and efficient transformer inference on edge clusters. Journal of Systems Architecture. 2026;177:103861. doi:10.1016/j.sysarc.2026.103861
BibTeX
@article{Wang2026,
author = {Wang, Wanqi and Jing, Boran and He, Shuyu and Song, Zheng and Fang, Weiwei},
title = {EdgeATP: An adaptive tensor parallelism framework for scalable and efficient transformer inference on edge clusters},
journal = {Journal of Systems Architecture},
year = {2026},
volume = {177},
pages = {103861},
doi = {10.1016/j.sysarc.2026.103861}
}
EUVIMED