CADE: Context-aware dispatch engine for energy-efficient VLM inference on heterogeneous edge with discrete neural processing units
Journal of Systems Architecture · 2026-12 · 181 · 104016
DOI: 10.1016/j.sysarc.2026.104016 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Systems Architecture, 2026-12. Verfasst von Seongjin Yun und 1 weiteren Autor:innen. Die Arbeit nennt 51 Literaturangaben. Gefördert von: Institute for Information and Communications Technology Promotion.
Abstract (Originalsprache)
Kein Abstract verfügbar.
Förderung
- Institute for Information and Communications Technology Promotion
Zitieren
APA
Yun, S., & Kim, J. (2026). CADE: Context-aware dispatch engine for energy-efficient VLM inference on heterogeneous edge with discrete neural processing units. Journal of Systems Architecture, 181, 104016. https://doi.org/10.1016/j.sysarc.2026.104016
Vancouver
Yun S, Kim J. CADE: Context-aware dispatch engine for energy-efficient VLM inference on heterogeneous edge with discrete neural processing units. Journal of Systems Architecture. 2026;181:104016. doi:10.1016/j.sysarc.2026.104016
BibTeX
@article{Yun2026,
author = {Yun, Seongjin and Kim, Jeong-Si},
title = {CADE: Context-aware dispatch engine for energy-efficient VLM inference on heterogeneous edge with discrete neural processing units},
journal = {Journal of Systems Architecture},
year = {2026},
volume = {181},
pages = {104016},
doi = {10.1016/j.sysarc.2026.104016}
}
EUVIMED