CoMoE: Collaborative Optimization of Expert Aggregation and Offloading for MoE-based LLMs at Edge

TL;DR

CoMoE is a dynamic, resource-aware framework that optimizes expert aggregation and offloading for large language models at mobile edge devices, significantly reducing memory and latency while maintaining performance.

Contribution

It introduces a novel adaptive optimization framework for MoE deployment in mobile edge environments, addressing expert aggregation and offloading challenges dynamically.

Findings

70% memory reduction compared to baselines

10.5% lower inference latency than existing methods

Enables deployment of large-scale MoE models on resource-constrained devices

Abstract

The proliferation of large language models (LLMs) has driven the adoption of Mixture-of-Experts (MoE) architectures as a promising solution to scale model capacity while controlling computational costs. However, deploying MoE models in resource-constrained mobile edge computing environments presents significant challenges due to their large memory footprint and dynamic expert activation patterns. To address these challenges, we propose a novel dynamic resource-aware collaborative optimization framework that jointly optimizes expert aggregation granularity and offloading strategies based on real-time device resource states, network conditions, and input characteristics in mobile edge environments, denoted as CoMoE. In CoMoE, we first systematically analyze existing expert aggregation techniques, including expert parameter merging,knowledge distillation,and parameter sharing decomposition, identifying their limitations in dynamic mobile environments.We then investigate expert offloading strategies encompassing expert prediction and prefetching, expert caching and scheduling, and multi-tier storage architectures, revealing the interdependencies between routing decisions and offloading performance.The CoMoE incorporates adaptive scheduling mechanisms that respond to user mobility and varying network conditions, enabling efficient MoE deployment across heterogeneous edge devices. Extensive experiments on real mobile edge testbeds demonstrate that CoMoE achieves approximately 70% reduction in memory usage compared to baseline methods, 10.5% lower inference latency than existing expert offloading techniques, while maintaining model performance stability. For large-scale MoE models (e.g,7.4B-parameter Switch-Base-128), the CoMoE reduces memory requirements from 15.6GB to 4.7GB, enabling deployment on resource-constrained mobile edge devices that previously could only support much smaller models.