# Optimizing Mixture-of-Experts Inference Time Combining Model Deployment and Communication Scheduling

arXiv: https://arxiv.org/abs/2410.17043 · HTML: https://mlsanity.com/paper/2410.17043/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Efficient MoE training and inference systems, one of 12 directions in Mixture-of-experts.
- Builds on 21 of its 43 references that are in the map.
- First posted on arXiv 22 Oct 2024.

## Placed in

- Mixture-of-experts / [Efficient MoE training and inference systems](https://mlsanity.com/moe/efficient-moe-training-and-inference-systems/)

## Builds on (most cited first, 21 of 21)

- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism](https://mlsanity.com/paper/1909.08053/) (2019)
- [GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding](https://mlsanity.com/paper/2006.16668/) (2020)
- [Generating Long Sequences with Sparse Transformers](https://mlsanity.com/paper/1904.10509/) (2019)
- [ZeRO: Memory Optimizations Toward Training Trillion Parameter Models](https://mlsanity.com/paper/1910.02054/) (2019)
- [Scaling Vision with Sparse Mixture of Experts](https://mlsanity.com/paper/2106.05974/) (2021)
- [DeepSpeed-MoE: Advancing Mixture-of-Experts Inference and Training to Power Next-Generation AI Scale](https://mlsanity.com/paper/2201.05596/) (2022)
- [Multimodal Contrastive Learning with LIMoE: the Language-Image Mixture of Experts](https://mlsanity.com/paper/2206.02770/) (2022)
- [Tutel: Adaptive Mixture-of-Experts at Scale](https://mlsanity.com/paper/2206.03382/) (2022)
- [FastMoE: A Fast Mixture-of-Expert Training System](https://mlsanity.com/paper/2103.13262/) (2021)
- [Accelerating Distributed MoE Training and Inference with Lina](https://mlsanity.com/paper/2210.17223/) (2022)
- [Pre-gated MoE: An Algorithm-System Co-Design for Fast and Scalable Mixture-of-Expert Inference](https://mlsanity.com/paper/2308.12066/) (2023)
- [Heterogeneity-Aware Cluster Scheduling Policies for Deep Learning Workloads](https://mlsanity.com/paper/2008.09213/) (2020)
- [FlexMoE: Scaling Large-scale Sparse Pre-trained Model Training via Dynamic Device Placement](https://mlsanity.com/paper/2304.03946/) (2023)
- [MoESys: A Distributed and Efficient Mixture-of-Experts Training and Inference System for Internet Services](https://mlsanity.com/paper/2205.10034/) (2022)
- [Towards MoE Deployment: Mitigating Inefficiencies in Mixture-of-Expert (MoE) Inference](https://mlsanity.com/paper/2303.06182/) (2023)
- [HetuMoE: An Efficient Trillion-scale Mixture-of-Expert Distributed Training System](https://mlsanity.com/paper/2203.14685/) (2022)
- [TA-MoE: Topology-Aware Large Scale Mixture-of-Expert Training](https://mlsanity.com/paper/2302.09915/) (2023)
- [Lazarus: Resilient and Elastic Training of Mixture-of-Experts Models](https://mlsanity.com/paper/2407.04656/) (2024)
- [HAP: SPMD DNN Training on Heterogeneous GPU Clusters with Automated Program Synthesis](https://mlsanity.com/paper/2401.05965/) (2024)

## Built on by (most cited first, 7 of 7)

- [A Survey on Inference Optimization Techniques for Mixture of Experts Models](https://mlsanity.com/paper/2412.14219/) (2024)
- [Taming the Titans: A Survey of Efficient LLM Inference Serving](https://mlsanity.com/paper/2504.19720/) (2025)
- [Patterns behind Chaos: Forecasting Data Movement for Efficient Large-Scale MoE LLM Inference](https://mlsanity.com/paper/2510.05497/) (2025)
- [SpaceMoE: Realizing Distributed Mixture-of-Experts Inference over Space Networks](https://mlsanity.com/paper/2605.00515/) (2026)
- [Unlock the Potential of Fine-grained LLM Serving via Dynamic Module Scaling](https://mlsanity.com/paper/2507.18006/) (2025)
- [RailS: Load Balancing for All-to-All Communication in Distributed Mixture-of-Experts Training](https://mlsanity.com/paper/2510.19262/) (2025)
- [Puzzle: Scheduling Multiple Deep Learning Models on Mobile Device with Heterogeneous Processors](https://mlsanity.com/paper/2508.17764/) (2025)

## Abstract (arXiv)

As machine learning models scale in size and complexity, their computational requirements become a significant barrier. Mixture-of-Experts (MoE) models alleviate this issue by selectively activating relevant experts. Despite this, MoE models are hindered by high communication overhead from all-to-all operations, low GPU utilization due to the synchronous communication constraint, and complications from heterogeneous GPU environments. This paper presents Aurora, which optimizes both model deployment and all-to-all communication scheduling to address these challenges in MoE inference. Aurora achieves minimal communication times by strategically ordering token transmissions in all-to-all communications. It improves GPU utilization by colocating experts from different models on the same device, avoiding the limitations of synchronous all-to-all communication. We analyze Aurora's optimization strategies theoretically across four common GPU cluster settings: exclusive vs. colocated models on GPUs, and homogeneous vs. heterogeneous GPUs. Aurora provides optimal solutions for three cases, and for the remaining NP-hard scenario, it offers a polynomial-time sub-optimal solution with only a 1.07x degradation from the optimal. Aurora is the first approach to minimize MoE inference time via optimal model deployment and communication scheduling across various scenarios. Evaluations demonstrate that Aurora significantly accelerates inference, achieving speedups of up to 2.38x in homogeneous clusters and 3.54x in heterogeneous environments. Moreover, Aurora enhances GPU utilization by up to 1.5x compared to existing methods.