# EPS-MoE: Expert Pipeline Scheduler for Cost-Efficient MoE Inference

arXiv: https://arxiv.org/abs/2410.12247 · HTML: https://mlsanity.com/paper/2410.12247/

## Key facts

- Cited by 6 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 27 of its 31 references that are in the map.
- First posted on arXiv 16 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, 27 of 27)

- [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)
- [DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model](https://mlsanity.com/paper/2405.04434/) (2024)
- [DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving](https://mlsanity.com/paper/2401.09670/) (2024)
- [Splitwise: Efficient generative LLM inference using phase splitting](https://mlsanity.com/paper/2311.18677/) (2023)
- [Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve](https://mlsanity.com/paper/2403.02310/) (2024)
- [DeepSpeed-MoE: Advancing Mixture-of-Experts Inference and Training to Power Next-Generation AI Scale](https://mlsanity.com/paper/2201.05596/) (2022)
- [ST-MoE: Designing Stable and Transferable Sparse Expert Models](https://mlsanity.com/paper/2202.08906/) (2022)
- [Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving](https://mlsanity.com/paper/2407.00079/) (2024)
- [Scaling Laws for Fine-Grained Mixture of Experts](https://mlsanity.com/paper/2402.07871/) (2024)
- [LLM Inference Unveiled: Survey and Roofline Model Insights](https://mlsanity.com/paper/2402.16363/) (2024)
- [Inference without Interference: Disaggregate LLM Inference for Mixed Downstream Workloads](https://mlsanity.com/paper/2401.11181/) (2024)
- [Vidur: A Large-Scale Simulation Framework For LLM Inference](https://mlsanity.com/paper/2405.05465/) (2024)
- [FastMoE: A Fast Mixture-of-Expert Training System](https://mlsanity.com/paper/2103.13262/) (2021)
- [NanoFlow: Towards Optimal Large Language Model Serving Throughput](https://mlsanity.com/paper/2408.12757/) (2024)
- [Arctic-Embed: Scalable, Efficient, and Accurate Text Embedding Models](https://mlsanity.com/paper/2405.05374/) (2024)
- [Distributed Hierarchical GPU Parameter Server for Massive Scale Deep Learning Ads Systems](https://mlsanity.com/paper/2003.05622/) (2020)
- [FlexMoE: Scaling Large-scale Sparse Pre-trained Model Training via Dynamic Device Placement](https://mlsanity.com/paper/2304.03946/) (2023)
- [A Hybrid Tensor-Expert-Data Parallelism Approach to Optimize Mixture-of-Experts Training](https://mlsanity.com/paper/2303.06318/) (2023)
- [HetuMoE: An Efficient Trillion-scale Mixture-of-Expert Distributed Training System](https://mlsanity.com/paper/2203.14685/) (2022)
- [Shortcut-connected Expert Parallelism for Accelerating Mixture-of-Experts](https://mlsanity.com/paper/2404.05019/) (2024)
- [HMoE: Heterogeneous Mixture of Experts for Language Modeling](https://mlsanity.com/paper/2408.10681/) (2024)
- [Who Says Elephants Can't Run: Bringing Large Scale MoE Models into Cloud Scale Production](https://mlsanity.com/paper/2211.10017/) (2022)
- [P/D-Serve: Serving Disaggregated Large Language Model at Scale](https://mlsanity.com/paper/2408.08147/) (2024)
- [Scattered Mixture-of-Experts Implementation](https://mlsanity.com/paper/2403.08245/) (2024)

## Built on by (most cited first, 6 of 6)

- [LongCat-Flash Technical Report](https://mlsanity.com/paper/2509.01322/) (2025)
- [A Survey on Inference Optimization Techniques for Mixture of Experts Models](https://mlsanity.com/paper/2412.14219/) (2024)
- [Scaling Embeddings Outperforms Scaling Experts in Language Models](https://mlsanity.com/paper/2601.21204/) (2026)
- [Semantic Parallelism: Redefining Efficient MoE Inference via Model-Data Co-Scheduling](https://mlsanity.com/paper/2503.04398/) (2025)
- [MoE-Prefill: Zero Redundancy Overheads in MoE Prefill Serving](https://mlsanity.com/paper/2605.02960/) (2026)
- [HDA-MoE: Hybrid Parallelism and Dynamic, Adaptive Scheduling for Mixture-of-Experts with 3D Near-Memory Processing](https://mlsanity.com/paper/2609.08682/) (2026)

## Abstract (arXiv)

The Mixture-of-Experts (MoE) model has emerged as a prominent architecture in the field of Large Language Models (LLMs), providing a better balance between model performance and computational efficiency. However the General Matrix Multiply (GEMM) operations and large parameters introduce challenges related to computational efficiency and communication overhead, which become throughput bottlenecks during inference. Applying a single parallelism strategy like EP, DP, TP or a straightforward combination of them to MoE usually achieves sub-optimal inference throughput. This paper introduces EPS-MoE, a novel expert pipeline scheduler for MoE that surpasses the existing parallelism schemes. Our approach optimizes the computation of MoE FeedForward Network (FFN) modules by dynamically selecting the best kernel implementation of GroupGemm and DenseGemm for different loads and adaptively overlapping these computations with communication, leading to a substantial increase in throughput. Our experimental results demonstrate at most 52.4% improvement in prefill throughput compared to existing parallel inference methods. Specifically, our method accelerated the highly optimized DeepSeekV2 model from a claimed 100K tokens per second to at least 120K tokens per second.