EUVIMEDEUVIMED entdecken
Crossref

Enabling Distributed Cooperative Full-Size LLM Inference With Tensor Parallelism Across Heterogeneous Edge Devices

Yaodong Huang, Weixuan Peng, Yi Guo, Lin Zhu, Laizhong Cui

IEEE Transactions on Computers · 2026-12 · 75 (12) · 4506-4520

DOI: 10.1109/tc.2026.3733643 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Computers, 2026-12. Verfasst von Yaodong Huang und 4 weiteren Autor:innen. Die Arbeit nennt 37 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Guangdong Basic and Applied Basic Research Foundation, Shenzhen Science and Technology Program.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Kein Abstract verfügbar.

Förderung

  • National Natural Science Foundation of China
  • Guangdong Basic and Applied Basic Research Foundation
  • Shenzhen Science and Technology Program
  • Research Team Cultivation Program of Shenzhen University
  • Open Research Fund from Guangdong Laboratory of Artificial Intelligence and Digital Economy
  • Scientific Foundation for Youth Scholars of Shenzhen University

Zitieren

APA

Huang, Y., Peng, W., Guo, Y., Zhu, L., & Cui, L. (2026). Enabling Distributed Cooperative Full-Size LLM Inference With Tensor Parallelism Across Heterogeneous Edge Devices. IEEE Transactions on Computers, 75(12), 4506-4520. https://doi.org/10.1109/tc.2026.3733643

Vancouver

Huang Y, Peng W, Guo Y, Zhu L, Cui L. Enabling Distributed Cooperative Full-Size LLM Inference With Tensor Parallelism Across Heterogeneous Edge Devices. IEEE Transactions on Computers. 2026;75(12):4506-4520. doi:10.1109/tc.2026.3733643

BibTeX
@article{Huang2026,
  author = {Huang, Yaodong and Peng, Weixuan and Guo, Yi and Zhu, Lin and Cui, Laizhong},
  title = {Enabling Distributed Cooperative Full-Size LLM Inference With Tensor Parallelism Across Heterogeneous Edge Devices},
  journal = {IEEE Transactions on Computers},
  year = {2026},
  volume = {75},
  number = {12},
  pages = {4506--4520},
  doi = {10.1109/tc.2026.3733643}
}
Kostenlos starten →