Edge Large AI Models: Revolutionizing 6G Networks

TL;DR

This paper explores the deployment of large AI models at the edge for 6G networks, addressing challenges like resource constraints and proposing frameworks for model training, deployment, and applications such as channel prediction.

Contribution

It introduces collaborative fine-tuning, full-parameter training, and microservice-based inference architectures for edge large AI models in 6G, along with application insights for air-interface design.

Findings

Proposed frameworks improve edge LAM deployment efficiency.

Microservice architecture enhances inference scalability.

Application of edge LAM in channel prediction and beamforming.

Abstract

Large artificial intelligence models (LAMs) possess human-like abilities to solve a wide range of real-world problems, exemplifying the potential of experts in various domains and modalities. By leveraging the communication and computation capabilities of geographically dispersed edge devices, edge LAM emerges as an enabling technology to empower the delivery of various real-time intelligent services in 6G. Unlike traditional edge artificial intelligence (AI) that primarily supports a single task using small models, edge LAM is featured by the need of the decomposition and distributed deployment of large models, and the ability to support highly generalized and diverse tasks. However, due to limited communication, computation, and storage resources over wireless networks, the vast number of trainable neurons and the substantial communication overhead pose a formidable hurdle to the practical deployment of edge LAMs. In this paper, we investigate the opportunities and challenges of edge LAMs from the perspectives of model decomposition and resource management. Specifically, we propose collaborative fine-tuning and full-parameter training frameworks, alongside a microservice-assisted inference architecture, to enhance the deployment of edge LAM over wireless networks. Additionally, we investigate the application of edge LAM in air-interface designs, focusing on channel prediction and beamforming. These innovative frameworks and applications offer valuable insights and solutions for advancing 6G technology.