🤖 AI Summary
To address the high latency, substantial bandwidth overhead, and data privacy risks associated with deploying large language models (LLMs) in sixth-generation (6G) mobile edge computing (MEC), this paper proposes the first multimodal LLM collaborative deployment architecture tailored for 6G edge environments. Methodologically, it innovatively integrates split learning/inference, parameter-efficient fine-tuning (PEFT), model quantization, and parameter-shared inference to jointly optimize edge resource constraints and model performance. The contributions are threefold: (1) a systematic identification and analysis of fundamental bottlenecks hindering LLM edge deployment; (2) the design of an end-to-end joint optimization framework unifying edge training and inference; and (3) theoretical foundations and practical technical pathways enabling lightweight, privacy-preserving, and low-latency LLM deployment for proximity-aware intelligent applications—such as robotics and telemedicine—in 6G MEC.
📝 Abstract
Large language models (LLMs), which have shown remarkable capabilities, are revolutionizing AI development and potentially shaping our future. However, given their multimodality, the status quo cloud-based deployment faces some critical challenges: 1) long response time; 2) high bandwidth costs; and 3) the violation of data privacy. 6G mobile edge computing (MEC) systems may resolve these pressing issues. In this article, we explore the potential of deploying LLMs at the 6G edge. We start by introducing killer applications powered by multimodal LLMs, including robotics and healthcare, to highlight the need for deploying LLMs in the vicinity of end users. Then, we identify the critical challenges for LLM deployment at the edge and envision the 6G MEC architecture for LLMs. Furthermore, we delve into two design aspects, i.e., edge training and edge inference for LLMs. In both aspects, considering the inherent resource limitations at the edge, we discuss various cutting-edge techniques, including split learning/inference, parameter-efficient fine-tuning, quantization, and parameter-sharing inference, to facilitate the efficient deployment of LLMs. This article serves as a position paper for thoroughly identifying the motivation, challenges, and pathway for empowering LLMs at the 6G edge.
