# Klotski: Efficient Mixture-of-Expert Inference via Expert-Aware Multi-Batch Pipeline

arXiv: https://arxiv.org/abs/2502.06888 · HTML: https://mlsanity.com/paper/2502.06888/

## Key facts

- Cited by 21 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 28 of its 47 references that are in the map.
- First posted on arXiv 9 Feb 2025.

## 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, 28 of 28)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [HuggingFace's Transformers: State-of-the-art Natural Language Processing](https://mlsanity.com/paper/1910.03771/) (2019)
- [Efficient Streaming Language Models with Attention Sinks](https://mlsanity.com/paper/2309.17453/) (2023)
- [GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers](https://mlsanity.com/paper/2210.17323/) (2022)
- [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)
- [DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models](https://mlsanity.com/paper/2401.06066/) (2024)
- [H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models](https://mlsanity.com/paper/2306.14048/) (2023)
- [DeepSpeed Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scale](https://mlsanity.com/paper/2207.00032/) (2022)
- [DeepSpeed-MoE: Advancing Mixture-of-Experts Inference and Training to Power Next-Generation AI Scale](https://mlsanity.com/paper/2201.05596/) (2022)
- [ZeRO-Offload: Democratizing Billion-Scale Model Training](https://mlsanity.com/paper/2101.06840/) (2021)
- [ZeRO-Infinity: Breaking the GPU Memory Wall for Extreme Scale Deep Learning](https://mlsanity.com/paper/2104.07857/) (2021)
- [OpenMoE: An Early Effort on Open Mixture-of-Experts Language Models](https://mlsanity.com/paper/2402.01739/) (2024)
- [RAPHAEL: Text-to-Image Generation via Large Mixture of Diffusion Paths](https://mlsanity.com/paper/2305.18295/) (2023)
- [Accelerating Distributed MoE Training and Inference with Lina](https://mlsanity.com/paper/2210.17223/) (2022)
- [DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inference](https://mlsanity.com/paper/2401.08671/) (2024)
- [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)
- [A Survey of Resource-efficient LLM and Multimodal Foundation Models](https://mlsanity.com/paper/2401.08092/) (2024)
- [Fiddler: CPU-GPU Orchestration for Fast Inference of Mixture-of-Experts Models](https://mlsanity.com/paper/2402.07033/) (2024)
- [SiDA-MoE: Sparsity-Inspired Data-Aware Serving for Efficient and Scalable Large Mixture-of-Experts Models](https://mlsanity.com/paper/2310.18859/) (2023)
- [Lightweight Deep Learning for Resource-Constrained Environments: A Survey](https://mlsanity.com/paper/2404.07236/) (2024)
- [Mixture of Quantized Experts (MoQE): Complementary Effect of Low-bit Quantization and Robustness](https://mlsanity.com/paper/2310.02410/) (2023)
- [STI: Turbocharge NLP Inference at the Edge via Elastic Pipelining](https://mlsanity.com/paper/2207.05022/) (2022)

## Built on by (most cited first, 21 of 21)

- [GRACE-MoE: Grouping and Replication with Locality-Aware Routing for Efficient Distributed MoE Inference](https://mlsanity.com/paper/2509.25041/) (2025)
- [LayerScope: Predictive Cross-Layer Scheduling for Efficient Multi-Batch MoE Inference on Legacy Servers](https://mlsanity.com/paper/2509.23638/) (2025)
- [Patterns behind Chaos: Forecasting Data Movement for Efficient Large-Scale MoE LLM Inference](https://mlsanity.com/paper/2510.05497/) (2025)
- [MoE-SpAc: Efficient MoE Inference Based on Speculative Activation Utility in Heterogeneous Edge Scenarios](https://mlsanity.com/paper/2603.09983/) (2026)
- [ZipMoE: Efficient On-Device MoE Serving via Lossless Compression and Cache-Affinity Scheduling](https://mlsanity.com/paper/2601.21198/) (2026)
- [MoE-Lens: Towards the Hardware Limit of High-Throughput MoE LLM Serving Under Resource Constraints](https://mlsanity.com/paper/2504.09345/) (2025)
- [PPAI: Enabling Personalized LLM Agent Interoperability for Collaborative Edge Intelligence](https://mlsanity.com/paper/2605.18067/) (2026)
- [FreeToken: Efficient Edge-Native MoE Serving with Bandwidth-Adaptive Execution](https://mlsanity.com/paper/2608.16157/) (2026)
- [Context-Aware Mixture-of-Experts Inference on CXL-Enabled GPU-NDP Systems](https://mlsanity.com/paper/2512.04476/) (2025)
- [DyMoE: Dynamic Expert Orchestration with Mixed-Precision Quantization for Efficient MoE Inference on Edge](https://mlsanity.com/paper/2603.19172/) (2026)
- [PagedWeight: Efficient MoE LLM Serving with Dynamic Quality-Aware Weight Quantization](https://mlsanity.com/paper/2607.16184/) (2026)
- [A Scheduling Framework for Efficient MoE Inference on Edge GPU-NDP Systems](https://mlsanity.com/paper/2601.03992/) (2026)
- [OmniMoE: An Efficient MoE by Orchestrating Atomic Experts at Scale](https://mlsanity.com/paper/2602.05711/) (2026)
- [TriMoE: Augmenting GPU with AMX-Enabled CPU and DIMM-NDP for High-Throughput MoE Inference via Offloading](https://mlsanity.com/paper/2603.01058/) (2026)
- [Expert Streaming: Accelerating Low-Batch MoE Inference via Multi-chiplet Architecture and Dynamic Expert Trajectory Scheduling](https://mlsanity.com/paper/2603.27624/) (2026)
- [FluxMoE: Decoupling Expert Residency for High-Performance MoE Serving](https://mlsanity.com/paper/2604.02715/) (2026)
- [Director: Accelerating Distributed MoE Serving via Online Proactive Expert Placement](https://mlsanity.com/paper/2607.08782/) (2026)
- [SpecPrefetch: Parameter-Efficient Expert Prefetching for Sparse MoE Foundation Models](https://mlsanity.com/paper/2607.24787/) (2026)
- [BigMoMo: Efficient Inference of Large-Scale MoE with Speculative Decoding on Mobile Devices](https://mlsanity.com/paper/2609.14643/) (2026)
- [ITC-MoE: Importance-guided Token-aware Compression for MoE Diffusion Language Models](https://mlsanity.com/paper/2610.01296/) (2026)
- [Cascadia: Resident 975B MoE Inference on Eleven AI PCs](https://mlsanity.com/paper/2610.07219/) (2026)

## Abstract (arXiv)

Mixture of Experts (MoE), with its distinctive sparse structure, enables the scaling of language models up to trillions of parameters without significantly increasing computational costs. However, the substantial parameter size presents a challenge for inference, as the expansion in GPU memory cannot keep pace with the growth in parameters. Although offloading techniques utilise memory from the CPU and disk and parallelise the I/O and computation for efficiency, the computation for each expert in MoE models is often less than the I/O, resulting in numerous bubbles in the pipeline. Therefore, we propose Klotski, an efficient MoE inference engine that significantly reduces pipeline bubbles through a novel expert-aware multi-batch pipeline paradigm. The proposed paradigm uses batch processing to extend the computation time of the current layer to overlap with the loading time of the next layer. Although this idea has been effectively applied to dense models, more batches may activate more experts in the MoE, leading to longer loading times and more bubbles. Thus, unlike traditional approaches, we balance computation and I/O time and minimise bubbles by orchestrating their inference orders based on their heterogeneous computation and I/O requirements and activation patterns under different batch numbers. Moreover, to adapt to different hardware environments and models, we design a constraint-sensitive I/O-compute planner and a correlation-aware expert prefetcher for a schedule that minimises pipeline bubbles. Experimental results demonstrate that Klotski achieves a superior throughput-latency trade-off compared to state-of-the-art techniques, with throughput improvements of up to 85.12x.