Adaptive Layer Splitting for Wireless LLM Inference in Edge Computing: A Model-Based Reinforcement Learning Approach
It addresses efficient and private LLM inference in decentralized edge computing environments, representing an incremental improvement with a novel method for a known bottleneck.
This study tackled the problem of optimizing large language model (LLM) deployment in edge computing by analyzing splitting points and introducing a model-based reinforcement learning framework to determine the optimal split between edge and user equipment, resulting in effective balancing of inference performance and computational load under varying network conditions.
Optimizing the deployment of large language models (LLMs) in edge computing environments is critical for enhancing privacy and computational efficiency. Toward efficient wireless LLM inference in edge computing, this study comprehensively analyzes the impact of different splitting points in mainstream open-source LLMs. On this basis, this study introduces a framework taking inspiration from model-based reinforcement learning (MBRL) to determine the optimal splitting point across the edge and user equipment (UE). 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.