# OD-MoE: On-Demand Expert Loading for Cacheless Edge-Distributed MoE Inference

arXiv: https://arxiv.org/abs/2512.03927 · HTML: https://mlsanity.com/paper/2512.03927/

## Key facts

- Cited by 1 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 30 of its 48 references that are in the map.
- First posted on arXiv 3 Dec 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 30)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them](https://mlsanity.com/paper/2210.09261/) (2022)
- [A Survey of Quantization Methods for Efficient Neural Network Inference](https://mlsanity.com/paper/2103.13630/) (2021)
- [TinyLlama: An Open-Source Small Language Model](https://mlsanity.com/paper/2401.02385/) (2024)
- [BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions](https://mlsanity.com/paper/2406.15877/) (2024)
- [Model compression via distillation and quantization](https://mlsanity.com/paper/1802.05668/) (2018)
- [MT-Bench-101: A Fine-Grained Benchmark for Evaluating Large Language Models in Multi-Turn Dialogues](https://mlsanity.com/paper/2402.14762/) (2024)
- [MobileVLM V2: Faster and Stronger Baseline for Vision Language Model](https://mlsanity.com/paper/2402.03766/) (2024)
- [LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs](https://mlsanity.com/paper/2408.07055/) (2024)
- [The Good, The Bad, and The Greedy: Evaluation of LLMs Should Not Ignore Non-Determinism](https://mlsanity.com/paper/2407.10457/) (2024)
- [PowerInfer-2: Fast Large Language Model Inference on a Smartphone](https://mlsanity.com/paper/2406.06282/) (2024)
- [Fast Inference of Mixture-of-Experts Language Models with Offloading](https://mlsanity.com/paper/2312.17238/) (2023)
- [MoE-Lightning: High-Throughput MoE Inference on Memory-constrained GPUs](https://mlsanity.com/paper/2411.11217/) (2024)
- [HOBBIT: A Mixed Precision Expert Offloading System for Fast MoE Inference](https://mlsanity.com/paper/2411.01433/) (2024)
- [A Survey on Inference Optimization Techniques for Mixture of Experts Models](https://mlsanity.com/paper/2412.14219/) (2024)
- [AdapMoE: Adaptive Sensitivity-based Expert Gating and Management for Efficient MoE Inference](https://mlsanity.com/paper/2408.10284/) (2024)
- [WDMoE: Wireless Distributed Large Language Models with Mixture of Experts](https://mlsanity.com/paper/2405.03131/) (2024)
- [DAOP: Data-Aware Offloading and Predictive Pre-Calculation for Efficient MoE Inference](https://mlsanity.com/paper/2501.10375/) (2024)
- [GRACE-MoE: Grouping and Replication with Locality-Aware Routing for Efficient Distributed MoE Inference](https://mlsanity.com/paper/2509.25041/) (2025)
- [ChemMiner: A Large Language Model Agent System for Chemical Literature Data Mining](https://mlsanity.com/paper/2402.12993/) (2024)
- [SlimCaching: Edge Caching of Mixture-of-Experts for Distributed Inference](https://mlsanity.com/paper/2507.06567/) (2025)
- [KnowGuard: Knowledge-Driven Abstention for Multi-Round Clinical Reasoning](https://mlsanity.com/paper/2509.24816/) (2025)
- [The MoE-Empowered Edge LLMs Deployment: Architecture, Challenges, and Opportunities](https://mlsanity.com/paper/2502.08381/) (2025)
- [From Score Distributions to Balance: Plug-and-Play Mixture-of-Experts Routing](https://mlsanity.com/paper/2510.03293/) (2025)
- [LLMind 2.0: Distributed IoT Automation with Natural Language M2M Communication and Lightweight LLM Agents](https://mlsanity.com/paper/2508.13920/) (2025)

## Built on by (most cited first, 1 of 1)

- [OLED-MoE: Accelerating MoE-Based dLLM Inference via Inter-Iteration Locality-Aware Expert Offloading](https://mlsanity.com/paper/2609.33385/) (2026)

## Abstract (arXiv)

Mixture-of-Experts (MoE), while offering significant advantages as a Large Language Model (LLM) architecture, faces substantial challenges when deployed on low-cost edge devices with tight memory constraints. Expert offloading mitigates this issue by storing expert parameters in CPU memory and caching a subset of popular experts in GPU memory. Although this approach improves GPU memory utilization by caching only the likely-used experts, the GPU memory reserved for expert caching is underutilized compared with dense LLMs. This paper presents OD-MoE, a distributed MoE inference framework that obviates the need for expert caches via fully on-demand expert loading. OD-MoE is built upon two key mechanisms: 1) parallelizing expert loading and expert computation across distributed edge nodes, and 2) an ultra-accurate emulative predictor that forecasts expert activations multiple layers ahead while expert computation is ongoing. With these innovations, OD-MoE dynamically loads each target expert to one of the distributed nodes just-in-time before its activation and promptly evicts it afterward, freeing GPU memory for subsequent experts. We comprehensively benchmark OD-MoE against state-of-the-art MoE offloading systems on a ten-node testbed. Experimental results show that: 1) OD-MoE achieves 99.94% expert activation prediction accuracy, substantially surpassing all existing methods; and 2) OD-MoE delivers approximately 75% of the decoding speed of a fully GPU-cached MoE deployment while using only 1/3 of the GPU memory. More importantly, by eliminating the need for expert caches, OD-MoE enables MoE inference on edge nodes with less-than-1GB GPU memory, paving the way for practical MoE deployment of low-cost IoT devices at the edge in the LLM era.