Adaptive layer splitting for wireless large language model inference in edge computing: a model-based reinforcement learning approach

Yuxuan CHEN; Rongpeng LI; Xiaoxue YU; Zhifeng ZHAO; Honggang ZHANG

doi:10.1631/FITEE.2400468

Your Location：

Home >

Browse articles >

Adaptive layer splitting for wireless large language model inference in edge computing: a model-based reinforcement learning approach

Special Issue on Artificial-Intelligence-Empowered Digital-Twin-Based Network Autonomy | Updated：2025-03-13

- Adaptive layer splitting for wireless large language model inference in edge computing: a model-based reinforcement learning approach
  Enhanced Publication
- 基于模型强化学习的边缘计算无线大语言模型推理自适应层切分方法
- “In the field of edge computing, this study introduces a framework inspired by model-based reinforcement learning to optimize the deployment of large language models, significantly reducing computational costs and balancing inference performance and computational load under various network conditions.”
- Frontiers of Information Technology & Electronic Engineering Vol. 26, Issue 2, Pages: 278-292(2025)
- Affiliations：
  
  1.College of Information Science & Electronic Engineering, Zhejiang University, Hangzhou 310027, China
  2.Zhejiang Lab, Hangzhou 310012, China
- Author bio：
  
  E-mail: cyx00@zju.edu.cn
  ‡Corresponding author
  sdwhyxx@zju.edu.cn
  zhaozf@zhejianglab.com
  honggangzhang@zju.edu.cn
- Funds：
- DOI：10.1631/FITEE.2400468
  CLC： TP391
- Received：01 June 2024，
  
  Revised：13 September 2024，
  
  Published：2025-02
- Accepted：
Scan QR Code
Yuxuan CHEN, Rongpeng LI, Xiaoxue YU, et al. Adaptive layer splitting for wireless large language model inference in edge computing: a model-based reinforcement learning approach[J]. Frontiers of information technology & electronic engineering, 2025, 26(2): 278-292.
DOI：

Yuxuan CHEN, Rongpeng LI, Xiaoxue YU, et al. Adaptive layer splitting for wireless large language model inference in edge computing: a model-based reinforcement learning approach[J]. Frontiers of information technology & electronic engineering, 2025, 26(2): 278-292. DOI： 10.1631/FITEE.2400468.

Views

Downloads

CSCD

Alert me when the article has been cited

Submit

Tools

Publicity Resources

A cloud-edge-device collaborative offloading scheme with heterogeneous tasks and its performance evaluation

EdgeKeeper: a trusted edge computing framework for ubiquitous power Internet of Things

Cost-effective resource segmentation in hierarchical mobile edge clouds

Related Author

Xiaojun BAI

Yang ZHANG

Haixing WU

Yuting WANG

Shunfu JIN

Weiyong YANG

Wei LIU

Xingshen WEI

Related Institution

School of Information Science and Engineering, Yanshan University

Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province, Yanshan University

Department of Computer Science and Technology, Nanjing University

NARI Group Co., Ltd.

School of Electronic and Information Engineering, Beijing Jiaotong University

Intro

Map

Chat

Address：Zhejiang University Press, 148 Tianmushan Road, Hangzhou, China Postal code：310028
Tel：+86-571-88273162 Email：fitee@zju.edu.cn
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰

Adaptive layer splitting for wireless large language model inference in edge computing: a model-based reinforcement learning approach

DOI：10.1631/FITEE.2400468