# Patterns behind Chaos: Forecasting Data Movement for Efficient Large-Scale MoE LLM Inference

arXiv: https://arxiv.org/abs/2510.05497 · HTML: https://mlsanity.com/paper/2510.05497/

## 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 46 of its 98 references that are in the map.
- First posted on arXiv 7 Oct 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, 30 of 46)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://mlsanity.com/paper/2403.07974/) (2024)
- [MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark](https://mlsanity.com/paper/2406.01574/) (2024)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference](https://mlsanity.com/paper/2403.04132/) (2024)
- [SGLang: Efficient Execution of Structured Language Model Programs](https://mlsanity.com/paper/2312.07104/) (2023)
- [CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation](https://mlsanity.com/paper/2109.00859/) (2021)
- [DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models](https://mlsanity.com/paper/2401.06066/) (2024)
- [DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving](https://mlsanity.com/paper/2401.09670/) (2024)
- [FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU](https://mlsanity.com/paper/2303.06865/) (2023)
- [Kimi K2: Open Agentic Intelligence](https://mlsanity.com/paper/2507.20534/) (2025)
- [OLMoE: Open Mixture-of-Experts Language Models](https://mlsanity.com/paper/2409.02060/) (2024)
- [Using an LLM to Help With Code Understanding](https://mlsanity.com/paper/2307.08177/) (2023)
- [Tutel: Adaptive Mixture-of-Experts at Scale](https://mlsanity.com/paper/2206.03382/) (2022)
- [LoongServe: Efficiently Serving Long-Context Large Language Models with Elastic Sequence Parallelism](https://mlsanity.com/paper/2404.09526/) (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)
- [Hunyuan-Large: An Open-Source MoE Model with 52 Billion Activated Parameters by Tencent](https://mlsanity.com/paper/2411.02265/) (2024)
- [MoE-Lightning: High-Throughput MoE Inference on Memory-constrained GPUs](https://mlsanity.com/paper/2411.11217/) (2024)
- [Fiddler: CPU-GPU Orchestration for Fast Inference of Mixture-of-Experts Models](https://mlsanity.com/paper/2402.07033/) (2024)
- [A Complete Survey on LLM-based AI Chatbots](https://mlsanity.com/paper/2406.16937/) (2024)
- [Comet: Fine-grained Computation-communication Overlapping for Mixture-of-Experts](https://mlsanity.com/paper/2502.19811/) (2025)
- [LLaMAX: Scaling Linguistic Horizons of LLM by Enhancing Translation Capabilities Beyond 100 Languages](https://mlsanity.com/paper/2407.05975/) (2024)
- [ASTRA-sim2.0: Modeling Hierarchical Networks and Disaggregated Systems for Large-model Training at Scale](https://mlsanity.com/paper/2303.14006/) (2023)
- [SiDA-MoE: Sparsity-Inspired Data-Aware Serving for Efficient and Scalable Large Mixture-of-Experts Models](https://mlsanity.com/paper/2310.18859/) (2023)
- [Duplex: A Device for Large Language Models with Mixture of Experts, Grouped Query Attention, and Continuous Batching](https://mlsanity.com/paper/2409.01141/) (2024)

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

- [Expert Streaming: Accelerating Low-Batch MoE Inference via Multi-chiplet Architecture and Dynamic Expert Trajectory Scheduling](https://mlsanity.com/paper/2603.27624/) (2026)
- [Diagnosing Overhead in Dispatch Operations: Cross-architecture Observatory](https://mlsanity.com/paper/2605.20982/) (2026)
- [Decoding the Skew: Distribution-Aware MoE Inference with Adaptive Kernel Dispatch](https://mlsanity.com/paper/2607.23099/) (2026)
- [Heterogeneous LLM Serving with General-Purpose Processing-Near-Memory for Retrieval-Based Sparse Attention](https://mlsanity.com/paper/2608.03555/) (2026)
- [MoE Expert Execution in Disaggregated LLM Serving with a High-Bandwidth ReRAM Near-Memory Architecture](https://mlsanity.com/paper/2608.13962/) (2026)
- [SeqMoE: Toward Full-Load Performance via Predictive and Graph-Compatible MoE Offloading](https://mlsanity.com/paper/2609.12978/) (2026)

## Abstract (arXiv)

Large-scale Mixture of Experts (MoE) Large Language Models (LLMs) have recently become the frontier open-weight models, achieving remarkable model capability similar to proprietary ones. But their random expert selection mechanism introduces significant data movement overhead that becomes the dominant bottleneck in multi-unit LLM serving systems. To understand the patterns underlying this data movement, we conduct comprehensive data-movement-centric profiling across four state-of-the-art large-scale MoE models released in 2025 (200B-1000B) using over 24,000 requests spanning diverse workloads. We perform systematic analysis from both temporal and spatial perspectives and distill six key insights to guide the design of diverse serving systems. We verify these insights on both future wafer-scale GPU architectures and existing GPU systems. On wafer-scale GPUs, lightweight architectural modifications guided by our insights yield a 6.6× average speedup across four 200B--1000B models. On existing GPU systems, our insights drive the design of a prefill-aware expert placement algorithm that achieves up to 1.25× speedup on MoE computation. Our work presents the first comprehensive data-centric analysis of large-scale MoE models together with a concrete design study applying the learned lessons. Our profiling traces are publicly available at hrefhttps://huggingface.co/datasets/core12345/MoEexpertselectiontracetextcolorbluehttps://huggingface.co/datasets/core12345/MoEexpertselectiontrace.