# ExpertFlow: Efficient Mixture-of-Experts Inference via Predictive Expert Caching and Token Scheduling

arXiv: https://arxiv.org/abs/2410.17954 · HTML: https://mlsanity.com/paper/2410.17954/

## Key facts

- Cited by 19 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 22 of its 37 references that are in the map.
- First posted on arXiv 23 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, 22 of 22)

- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [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)
- [GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers](https://mlsanity.com/paper/2210.17323/) (2022)
- [Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization](https://mlsanity.com/paper/1808.08745/) (2018)
- [ZeRO: Memory Optimizations Toward Training Trillion Parameter Models](https://mlsanity.com/paper/1910.02054/) (2019)
- [DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence](https://mlsanity.com/paper/2401.14196/) (2024)
- [DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models](https://mlsanity.com/paper/2401.06066/) (2024)
- [FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU](https://mlsanity.com/paper/2303.06865/) (2023)
- [DeepSpeed Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scale](https://mlsanity.com/paper/2207.00032/) (2022)
- [ZeRO-Offload: Democratizing Billion-Scale Model Training](https://mlsanity.com/paper/2101.06840/) (2021)
- [PowerInfer: Fast Large Language Model Serving with a Consumer-grade GPU](https://mlsanity.com/paper/2312.12456/) (2023)
- [OpenMoE: An Early Effort on Open Mixture-of-Experts Language Models](https://mlsanity.com/paper/2402.01739/) (2024)
- [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)
- [Fast Inference of Mixture-of-Experts Language Models with Offloading](https://mlsanity.com/paper/2312.17238/) (2023)
- [Task-Specific Expert Pruning for Sparse Mixture-of-Experts](https://mlsanity.com/paper/2206.00277/) (2022)
- [Fiddler: CPU-GPU Orchestration for Fast Inference of Mixture-of-Experts Models](https://mlsanity.com/paper/2402.07033/) (2024)
- [MoESys: A Distributed and Efficient Mixture-of-Experts Training and Inference System for Internet Services](https://mlsanity.com/paper/2205.10034/) (2022)
- [Mixture of Quantized Experts (MoQE): Complementary Effect of Low-bit Quantization and Robustness](https://mlsanity.com/paper/2310.02410/) (2023)
- [Cached Model-as-a-Resource: Provisioning Large Language Model Agents for Edge Intelligence in Space-air-ground Integrated Networks](https://mlsanity.com/paper/2403.05826/) (2024)
- [Efficient Heterogeneous Large Language Model Decoding with Model-Attention Disaggregation](https://mlsanity.com/paper/2405.01814/) (2024)

## Built on by (most cited first, 19 of 19)

- [ExpertFlow: Adaptive Expert Scheduling and Memory Coordination for Efficient MoE Inference](https://mlsanity.com/paper/2510.26730/) (2025)
- [Pre-Attention Expert Prediction and Prefetching for Mixture-of-Experts Large Language Models](https://mlsanity.com/paper/2511.10676/) (2025)
- [Remoe: Towards Efficient and Low-Cost MoE Inference in Serverless Computing](https://mlsanity.com/paper/2512.18674/) (2025)
- [CRAFT: Fine-Grained Cost-Aware Expert Replication For Efficient Mixture-of-Experts Serving](https://mlsanity.com/paper/2603.28768/) (2026)
- [Routing-Free Mixture-of-Experts](https://mlsanity.com/paper/2604.00801/) (2026)
- [Achieving Cloud-Grade SLOs for Local Mixture-of-Experts Inference through CPU-GPU Hybrid Design](https://mlsanity.com/paper/2606.10493/) (2026)
- [PagedWeight: Efficient MoE LLM Serving with Dynamic Quality-Aware Weight Quantization](https://mlsanity.com/paper/2607.16184/) (2026)
- [MoE-Compression: How the Compression Error of Experts Affects the Inference Accuracy of MoE Model?](https://mlsanity.com/paper/2509.07727/) (2025)
- [Cacheable by Design? Training Mixture-of-Experts Routers for Locality Against the Edge Memory-Bandwidth Wall: A Pre-Registered Negative Result with a Systems Measurement Study](https://mlsanity.com/paper/2608.18261/) (2026)
- [OmniMoE: An Efficient MoE by Orchestrating Atomic Experts at Scale](https://mlsanity.com/paper/2602.05711/) (2026)
- [Affinity Is Not Enough: Recovering the Free Energy Principle in Mixture-of-Experts](https://mlsanity.com/paper/2605.00604/) (2026)
- [Beyond Independent Optimization: Compression, MoE Routing, and Quantization Interactions in Multimodal Edge Intelligence](https://mlsanity.com/paper/2607.20981/) (2026)
- [SpecPrefetch: Parameter-Efficient Expert Prefetching for Sparse MoE Foundation Models](https://mlsanity.com/paper/2607.24787/) (2026)
- [Mixture-of-Experts Language Models Can Be Strong and Efficient Retrievers](https://mlsanity.com/paper/2609.13486/) (2026)
- [OLED-MoE: Accelerating MoE-Based dLLM Inference via Inter-Iteration Locality-Aware Expert Offloading](https://mlsanity.com/paper/2609.33385/) (2026)
- [MaskCoFT: Masked Co-Adaptive Fine-Tuning for Memory-Efficient MoE Inference](https://mlsanity.com/paper/2609.34077/) (2026)
- [MoRE: Scaling mixture of experts with hardware-aware low-rank routing](https://mlsanity.com/paper/2609.36301/) (2026)
- [Democratizing MoE inference on commodity GPUs with CoMoE](https://mlsanity.com/paper/2610.09424/) (2026)
- [QCATS: Query Context-Aware Transformer Slicing for Efficient Predictive Query Processing](https://mlsanity.com/paper/2610.09894/) (2026)

## Abstract (arXiv)

Sparse Mixture-of-Experts (MoE) models can outperform dense large language models at similar computation by activating only a small set of experts per token. However, stacking many expert modules introduces substantial parameter memory, which makes MoE models difficult to deploy in memory-constrained environments such as single-GPU devices. Offloading alleviates this issue by storing inactive experts in CPU memory and loading them on demand, but existing methods remain limited: static caches disregard input-dependent routing, and methods that train separate models to predict expert usage ahead of time are often inaccurate or require significant training cost. We propose ExpertFlow, a lightweight MoE inference system that addresses this routing dependency through three coordinated components: 1) a transformer-based routing path predictor that estimates expert usage across all MoE layers in a single forward pass, 2) a token scheduler that groups tokens with similar predicted routes to improve expert utilization, and 3) a predictive expert cache that loads only the required experts while correcting mispredictions at runtime. Together, these components enable efficient expert loading and execution, reducing GPU memory usage by up to 93.72% and improving inference throughput by up to 10x over strong offloading baselines on a single GPU.