# Pre-Attention Expert Prediction and Prefetching for Mixture-of-Experts Large Language Models

arXiv: https://arxiv.org/abs/2511.10676 · HTML: https://mlsanity.com/paper/2511.10676/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in MoE large language models, one of 12 directions in Mixture-of-experts.
- Builds on 27 of its 37 references that are in the map.
- First posted on arXiv 10 Nov 2025.

## Placed in

- Mixture-of-experts / [MoE large language models](https://mlsanity.com/moe/moe-large-language-models/)

## Builds on (most cited first, 27 of 27)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone](https://mlsanity.com/paper/2404.14219/) (2024)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding](https://mlsanity.com/paper/2006.16668/) (2020)
- [GLaM: Efficient Scaling of Language Models with Mixture-of-Experts](https://mlsanity.com/paper/2112.06905/) (2021)
- [DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models](https://mlsanity.com/paper/2401.06066/) (2024)
- [DeepSeek-V3 Technical Report](https://mlsanity.com/paper/2412.19437/) (2024)
- [Focal Loss for Dense Object Detection](https://mlsanity.com/paper/1708.02002/) (2017)
- [Auxiliary-Loss-Free Load Balancing Strategy for Mixture-of-Experts](https://mlsanity.com/paper/2408.15664/) (2024)
- [Accelerating Distributed MoE Training and Inference with Lina](https://mlsanity.com/paper/2210.17223/) (2022)
- [Hunyuan-Large: An Open-Source MoE Model with 52 Billion Activated Parameters by Tencent](https://mlsanity.com/paper/2411.02265/) (2024)
- [Harder Tasks Need More Experts: Dynamic Routing in MoE Models](https://mlsanity.com/paper/2403.07652/) (2024)
- [HOBBIT: A Mixed Precision Expert Offloading System for Fast MoE Inference](https://mlsanity.com/paper/2411.01433/) (2024)
- [MoE-Infinity: Efficient MoE Inference on Personal Machines with Sparsity-Aware Expert Cache](https://mlsanity.com/paper/2401.14361/) (2024)
- [MoETuner: Optimized Mixture of Expert Serving with Balanced Expert Placement and Token Routing](https://mlsanity.com/paper/2502.06643/) (2025)
- [ExpertFlow: Efficient Mixture-of-Experts Inference via Predictive Expert Caching and Token Scheduling](https://mlsanity.com/paper/2410.17954/) (2024)
- [Mixture of Sparse Attention: Content-Based Learnable Sparse Attention via Expert-Choice Routing](https://mlsanity.com/paper/2505.00315/) (2025)
- [Fate: Fast Edge Inference of Mixture-of-Experts Models via Cross-Layer Gate](https://mlsanity.com/paper/2502.12224/) (2025)
- [SP-MoE: Speculative Decoding and Prefetching for Accelerating MoE-based Model Inference](https://mlsanity.com/paper/2510.10302/) (2025)
- [AttentionPredictor: Temporal Patterns Matter for KV Cache Compression](https://mlsanity.com/paper/2502.04077/) (2025)
- [Advancing MoE Efficiency: A Collaboration-Constrained Routing (C2R) Strategy for Better Expert Parallelism Design](https://mlsanity.com/paper/2504.01337/) (2025)
- [UMoE: Unifying Attention and FFN with Shared Experts](https://mlsanity.com/paper/2505.07260/) (2025)
- [DuoServe-MoE: Dual-Phase Expert Prefetch and Caching for LLM Inference QoS Assurance](https://mlsanity.com/paper/2509.07379/) (2025)
- [Improving Routing in Sparse Mixture of Experts with Graph of Tokens](https://mlsanity.com/paper/2505.00792/) (2025)
- [Latent Prototype Routing: Achieving Near-Perfect Load Balancing in Mixture-of-Experts](https://mlsanity.com/paper/2506.21328/) (2025)
- [An Empirical Evaluation of Serverless Cloud Infrastructure for Large-Scale Data Processing](https://mlsanity.com/paper/2501.07771/) (2025)

## Built on by (most cited first, 4 of 4)

- [SpecPrefetch: Parameter-Efficient Expert Prefetching for Sparse MoE Foundation Models](https://mlsanity.com/paper/2607.24787/) (2026)
- [APEX: Adaptive Expert Prefetching for Memory-Efficient Edge MoE Inference](https://mlsanity.com/paper/2608.11688/) (2026)
- [Beyond Capacity: Scalable MoE LLM Inference via High-Bandwidth Flash with Direct GPU and HBM Paths](https://mlsanity.com/paper/2608.14333/) (2026)
- [SpecFit: Not All Draft Tokens Cost the Same in Offloaded MoE Inference](https://mlsanity.com/paper/2610.15417/) (2026)

## Abstract (arXiv)

Mixture-of-Experts (MoE) Large Language Models (LLMs) efficiently scale-up the model while keeping relatively low inference cost. As MoE models only activate part of the experts, related work has proposed expert prediction and caching methods to prefetch the experts for faster inference. However, existing approaches utilize the activations from the previous layer for prediction, incurring low accuracy and leave the first layer unoptimized. Applying complex layers or even training standalone networks for better prediction introduces high computation overhead. In this paper, we propose pre-attention expert prediction to achieve accurate and lightweight expert prefetching. The key insight is that some functions in LLMs are ranking-preserving, indicating that matching the ranking of selected experts using simple linear functions is possible. Therefore, we utilize the activations before the attention block in the same layer with 2 linear functions and ranking-aware loss to achieve accurate prediction, which also supports prefetching in the first layer. Our lightweight, pre-attention expert routers achieve 93.03% accuracy on DeepSeek V2 Lite, 94.69% on Qwen3-30B, and 97.62% on Phi-mini-MoE, showing about 15% improvement on absolute accuracy over the state-of-the-art methods.