S-GPT: Shape-aware graph partitioning and tuning for sustainable inference of large-scale deep neural networks
Journal of Systems Architecture · 2026-12 · 181 · 103992
DOI: 10.1016/j.sysarc.2026.103992 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Systems Architecture, 2026-12. Verfasst von Hongen Shao und 4 weiteren Autor:innen. Die Arbeit nennt 50 Literaturangaben. Gefördert von: China Scholarship Council.
Abstract (Originalsprache)
Kein Abstract verfügbar.
Förderung
- China Scholarship Council
Zitieren
APA
Shao, H., Chen, C., Fang, X., Zeng, Z., & Li, K. (2026). S-GPT: Shape-aware graph partitioning and tuning for sustainable inference of large-scale deep neural networks. Journal of Systems Architecture, 181, 103992. https://doi.org/10.1016/j.sysarc.2026.103992
Vancouver
Shao H, Chen C, Fang X, Zeng Z, Li K. S-GPT: Shape-aware graph partitioning and tuning for sustainable inference of large-scale deep neural networks. Journal of Systems Architecture. 2026;181:103992. doi:10.1016/j.sysarc.2026.103992
BibTeX
@article{Shao2026,
author = {Shao, Hongen and Chen, Cen and Fang, Xin and Zeng, Ziqian and Li, Keqin},
title = {S-GPT: Shape-aware graph partitioning and tuning for sustainable inference of large-scale deep neural networks},
journal = {Journal of Systems Architecture},
year = {2026},
volume = {181},
pages = {103992},
doi = {10.1016/j.sysarc.2026.103992}
}
EUVIMED