Technology Category
Machine Learning: Mixture of Experts (MoE)Planning, Routing, and Scheduling: Optimization of Spatio-temporal SystemsSearch and Optimization: Sampling/Simulation-based Search
A Survey on Inference Optimization Techniques for Mixture of Experts Models
🤖 AI Summary
To address cross-layer optimization challenges—including low inference speed, high energy consumption, and poor hardware utilization—in large-scale Mixture-of-Experts (MoE) model deployment, this paper proposes the first unified taxonomy spanning model, system, and hardware stacks. Methodologically, it integrates expert pruning, dynamic routing with load balancing, multi-granularity compression (pruning, quantization, distillation), distributed scheduling, and hardware-aware compilation. We innovatively establish a cross-layer co-optimization framework and open-source an actively maintained *Awesome MoE Inference* knowledge repository. Our contributions include a structured technical landscape that clarifies core challenges and evolutionary trends, significantly improving inference efficiency and energy efficiency—enabling low-latency, high-throughput, and power-efficient industrial MoE deployment.
Technology Category
Application Category
📝 Abstract
The emergence of large-scale Mixture of Experts (MoE) models represents a significant advancement in artificial intelligence, offering enhanced model capacity and computational efficiency through conditional computation. However, deploying and running inference on these models presents significant challenges in computational resources, latency, and energy efficiency. This comprehensive survey analyzes optimization techniques for MoE models across the entire system stack. We first establish a taxonomical framework that categorizes optimization approaches into model-level, system-level, and hardware-level optimizations. At the model level, we examine architectural innovations including efficient expert design, attention mechanisms, various compression techniques such as pruning, quantization, and knowledge distillation, as well as algorithm improvement including dynamic routing strategies and expert merging methods. At the system level, we investigate distributed computing approaches, load balancing mechanisms, and efficient scheduling algorithms that enable scalable deployment. Furthermore, we delve into hardware-specific optimizations and co-design strategies that maximize throughput and energy efficiency. This survey provides both a structured overview of existing solutions and identifies key challenges and promising research directions in MoE inference optimization. To facilitate ongoing updates and the sharing of cutting-edge advances in MoE inference optimization research, we have established a repository accessible at https://github.com/MoE-Inf/awesome-moe-inference/.
Problem
Research questions and friction points this paper is trying to address.
Massive Mixture of Experts (MoE) Models
Performance Optimization
Hardware Utilization
Innovation
Methods, ideas, or system contributions that make the work stand out.
MoE Model Optimization
Load Balancing and Scheduling
Hardware Efficiency Enhancement
🔎 Similar Papers
2024-10-03arXiv.orgCitations: 0
2024-07-12arXiv.orgCitations: 9
