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

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

연구 분야: Networking

학회: Frontiers of Information Technology & Electronic Engineering

Optimizing the deployment of large language models (LLMs) in edge computing environments is critical for enhancing privacy and computational efficiency. In the path toward efficient wireless LLM inference in edge computing, this study comprehensively analyzes the impact of different splitting points in mainstream open-source LLMs. Accordingly, this study introduces a framework taking inspiration from model-based reinforcement learning to determine the optimal splitting point across the edge and user equipment. By incorporating a reward surrogate model, our approach significantly reduces the computational cost of frequent performance evaluations. Extensive simulations demonstrate that this method effectively balances inference performance and computational load under varying network conditions, providing a robust solution for LLM deployment in decentralized settings.