BriefGPT.xyz
Jun, 2024
边缘计算中无线LLM推理的自适应分层切割：基于模型的强化学习方法
Adaptive Layer Splitting for Wireless LLM Inference in Edge Computing: A Model-Based Reinforcement Learning Approach
HTML
PDF
Yuxuan Chen, Rongpeng Li, Xiaoxue Yu, Zhifeng Zhao, Honggang Zhang
TL;DR
通过模型驱动的强化学习方法，该研究在边缘计算环境中最优化部署大型语言模型，提高隐私和计算效率，减少计算成本，并在分散式环境中实现了推理性能和计算负载的平衡。
Abstract
Optimizing the deployment of
large language models
(LLMs) in
edge computing
environments is critical for enhancing privacy and computational efficiency. Toward efficient
→