EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

DistMLLM: Enhancing Multimodal Large Language Model Serving in Heterogeneous Edge Computing

Xingyu Yuan iD, Hui Chen iD, Lei Liu, He Li iD

Sensors · 15.12.2025 · 25 (24) · 7612

DOI: 10.3390/s25247612 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 15.12.2025. Verfasst von Xingyu Yuan und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Sciences and Informatics, Muroran Institute of Technology, Muroran 050-8585, Hokkaido, Japan. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 17 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Japan Society for the Promotion of Science, New Energy and Industrial Technology Development Organization.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Multimodal Large Language Models (MLLMs) offer powerful capabilities for processing and generating text, image, and audio data, enabling real-time intelligence in diverse applications. Deploying MLLM services at the edge can reduce transmission latency and enhance responsiveness, but it also introduces significant challenges due to the high computational demands of these models and the heterogeneity of edge devices. In this paper, we propose DistMLLM, a profit-oriented framework that enables efficient MLLM service deployment in heterogeneous edge environments. DistMLLM disaggregates multimodal tasks into encoding and inference stages, assigning them to different devices based on capability. To optimize task allocation under uncertain device conditions and competing provider interests, it employs a multi-agent bandit algorithm that jointly learns and schedules encoder and inference tasks. Extensive simulations demonstrate that DistMLLM consistently achieves higher long-term profit and lower regret than strong baselines, offering a scalable and adaptive solution for edge-based MLLM services.

Schlagwörter

Stichwörter der Autor:innen

edge computinglarge language modelmulti-agent bandittask allocation

Autor:innen und Institutionen

  • Department of Sciences and Informatics, Muroran Institute of Technology, Muroran 050-8585, Hokkaido, Japan.
  • Guangzhou Institute of Technology, Xidian University, Guangzhou 510555, China.

ORCID-Profile: Xingyu Yuan, Hui Chen, He Li

Förderung

  • Japan Society for the Promotion of Science
  • New Energy and Industrial Technology Development Organization

Zitieren

APA

Yuan, X., Chen, H., Liu, L., & Li, H. (2025). DistMLLM: Enhancing Multimodal Large Language Model Serving in Heterogeneous Edge Computing. Sensors, 25(24), 7612. https://doi.org/10.3390/s25247612

Vancouver

Yuan X, Chen H, Liu L, Li H. DistMLLM: Enhancing Multimodal Large Language Model Serving in Heterogeneous Edge Computing. Sensors. 2025;25(24):7612. doi:10.3390/s25247612

BibTeX
@article{Yuan2025,
  author = {Yuan, Xingyu and Chen, Hui and Liu, Lei and Li, He},
  title = {DistMLLM: Enhancing Multimodal Large Language Model Serving in Heterogeneous Edge Computing},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {24},
  pages = {7612},
  doi = {10.3390/s25247612}
}
Kostenlos starten →