EUVIMEDEUVIMED entdecken
Crossref

Dynamic Grouped Attention and Hierarchical Cache Optimization for Low-Latency On-Device Large-Model Inference

WenTao Li, Jie Zhao, SongQuan Zhu, Zheng Zhang, He Li, and Ming Hui

IEEE Transactions on Mobile Computing · 2026 · 1-18

DOI: 10.1109/tmc.2026.3750329 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Mobile Computing, 2026. Verfasst von WenTao Li und 5 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Kein Abstract verfügbar.

Zitieren

APA

Li, W., Zhao, J., Zhu, S., Zhang, Z., Li, H., & Hui, A. M. (2026). Dynamic Grouped Attention and Hierarchical Cache Optimization for Low-Latency On-Device Large-Model Inference. IEEE Transactions on Mobile Computing, 1-18. https://doi.org/10.1109/tmc.2026.3750329

Vancouver

Li W, Zhao J, Zhu S, Zhang Z, Li H, Hui AM. Dynamic Grouped Attention and Hierarchical Cache Optimization for Low-Latency On-Device Large-Model Inference. IEEE Transactions on Mobile Computing. 2026:1-18. doi:10.1109/tmc.2026.3750329

BibTeX
@article{Li2026,
  author = {Li, WenTao and Zhao, Jie and Zhu, SongQuan and Zhang, Zheng and Li, He and Hui, and Ming},
  title = {Dynamic Grouped Attention and Hierarchical Cache Optimization for Low-Latency On-Device Large-Model Inference},
  journal = {IEEE Transactions on Mobile Computing},
  year = {2026},
  pages = {1--18},
  doi = {10.1109/tmc.2026.3750329}
}
Kostenlos starten →