# Fast MoE Inference via Predictive Prefetching and Expert Replication

arXiv: https://arxiv.org/abs/2605.11537 · HTML: https://mlsanity.com/paper/2605.11537/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Efficient MoE training and inference systems, one of 12 directions in Mixture-of-experts.
- Builds on 13 of its 27 references that are in the map.
- First posted on arXiv 12 May 2026.

## 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, 13 of 13)

- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding](https://mlsanity.com/paper/2006.16668/) (2020)
- [DeepSpeed-MoE: Advancing Mixture-of-Experts Inference and Training to Power Next-Generation AI Scale](https://mlsanity.com/paper/2201.05596/) (2022)
- [A Review of Sparse Expert Models in Deep Learning](https://mlsanity.com/paper/2209.01667/) (2022)
- [FastMoE: A Fast Mixture-of-Expert Training System](https://mlsanity.com/paper/2103.13262/) (2021)
- [Pre-gated MoE: An Algorithm-System Co-Design for Fast and Scalable Mixture-of-Expert Inference](https://mlsanity.com/paper/2308.12066/) (2023)
- [EdgeMoE: Empowering Sparse Large Language Models on Mobile Devices](https://mlsanity.com/paper/2308.14352/) (2023)
- [Simple Recurrent Units for Highly Parallelizable Recurrence](https://mlsanity.com/paper/1709.02755/) (2017)
- [JetMoE: Reaching Llama2 Performance with 0.1M Dollars](https://mlsanity.com/paper/2404.07413/) (2024)
- [HOBBIT: A Mixed Precision Expert Offloading System for Fast MoE Inference](https://mlsanity.com/paper/2411.01433/) (2024)
- [FlexMoE: Scaling Large-scale Sparse Pre-trained Model Training via Dynamic Device Placement](https://mlsanity.com/paper/2304.03946/) (2023)
- [A Survey on Inference Optimization Techniques for Mixture of Experts Models](https://mlsanity.com/paper/2412.14219/) (2024)
- [How does Architecture Influence the Base Capabilities of Pre-trained Language Models? A Case Study Based on FFN-Wider and MoE Transformers](https://mlsanity.com/paper/2403.02436/) (2024)

## Abstract (arXiv)

The Mixture of Experts (MoE) architecture has become a fundamental building block in state-of-the-art large language models (LLMs), improving domain-specific expertise in LLMs and scaling model capacity without proportionally increasing their computational overhead. However, MoE inference often suffers from suboptimal GPU utilization, load imbalance, and elevated latency arising from multiple tokens waiting on the same experts for their computation which arises from sparsity of expert activation. To address these challenges, we propose a dynamic expert replication strategy that predicts which experts are likely to be overloaded and replicates them for upcoming batches of tokens. The replicated experts process batch tokens concurrently across layers, which leads to improved parallelism, shorter GPU idle time, and significantly faster inference. Experimental evaluations conducted on large-scale MoE models, including Switch-base-128 and Switch-base-256, demonstrate that our method achieves near-complete GPU utilization (approx 100%), leading to upto 3x improvement in inference speed while preserving approximately 90-95% of the performance of baseline architectures