# SMoE: An Algorithm-System Co-Design for Pushing MoE to the Edge via Expert Substitution

arXiv: https://arxiv.org/abs/2508.18983 · HTML: https://mlsanity.com/paper/2508.18983/

## Key facts

- Cited by 3 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 32 of its 54 references that are in the map.
- First posted on arXiv 26 Aug 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 32)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [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)
- [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)
- [PIQA: Reasoning about Physical Commonsense in Natural Language](https://mlsanity.com/paper/1911.11641/) (2019)
- [DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models](https://mlsanity.com/paper/2401.06066/) (2024)
- [RACE: Large-scale ReAding Comprehension Dataset From Examinations](https://mlsanity.com/paper/1704.04683/) (2017)
- [DeepSpeed Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scale](https://mlsanity.com/paper/2207.00032/) (2022)
- [WiC: the Word-in-Context Dataset for Evaluating Context-Sensitive Meaning Representations](https://mlsanity.com/paper/1808.09121/) (2018)
- [A Survey on Mixture of Experts in Large Language Models](https://mlsanity.com/paper/2407.06204/) (2024)
- [PowerInfer: Fast Large Language Model Serving with a Consumer-grade GPU](https://mlsanity.com/paper/2312.12456/) (2023)
- [Accelerating LLM Inference with Staged Speculative Decoding](https://mlsanity.com/paper/2308.04623/) (2023)
- [Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models](https://mlsanity.com/paper/2402.14800/) (2024)
- [Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy](https://mlsanity.com/paper/2310.01334/) (2023)
- [PowerInfer-2: Fast Large Language Model Inference on a Smartphone](https://mlsanity.com/paper/2406.06282/) (2024)
- [MoE-Lightning: High-Throughput MoE Inference on Memory-constrained GPUs](https://mlsanity.com/paper/2411.11217/) (2024)
- [Task-Specific Expert Pruning for Sparse Mixture-of-Experts](https://mlsanity.com/paper/2206.00277/) (2022)
- [Meta-DMoE: Adapting to Domain Shift by Meta-Distillation from Mixture-of-Experts](https://mlsanity.com/paper/2210.03885/) (2022)
- [ProMoE: Fast MoE-based LLM Serving using Proactive Caching](https://mlsanity.com/paper/2410.22134/) (2024)
- [NEO: Saving GPU Memory Crisis with CPU Offloading for Online LLM Inference](https://mlsanity.com/paper/2411.01142/) (2024)
- [Edge-MoE: Memory-Efficient Multi-Task Vision Transformer Architecture with Task-level Sparsity via Mixture-of-Experts](https://mlsanity.com/paper/2305.18691/) (2023)
- [D2MoE: Dual Routing and Dynamic Scheduling for Efficient On-Device MoE-based LLM Serving](https://mlsanity.com/paper/2504.15299/) (2025)
- [ComPEFT: Compression for Communicating Parameter Efficient Updates via Sparsification and Quantization](https://mlsanity.com/paper/2311.13171/) (2023)
- [Cambricon-LLM: A Chiplet-Based Hybrid Architecture for On-Device Inference of 70B LLM](https://mlsanity.com/paper/2409.15654/) (2024)
- [HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference](https://mlsanity.com/paper/2504.05897/) (2025)
- [DAOP: Data-Aware Offloading and Predictive Pre-Calculation for Efficient MoE Inference](https://mlsanity.com/paper/2501.10375/) (2024)
- [The MoE-Empowered Edge LLMs Deployment: Architecture, Challenges, and Opportunities](https://mlsanity.com/paper/2502.08381/) (2025)
- [FLAME-MoE: A Transparent End-to-End Research Platform for Mixture-of-Experts Language Models](https://mlsanity.com/paper/2505.20225/) (2025)

## Built on by (most cited first, 3 of 3)

- [SliceMoE: Bit-Sliced Expert Caching under Miss-Rate Constraints for Efficient MoE Inference](https://mlsanity.com/paper/2512.12990/) (2025)
- [FreeToken: Efficient Edge-Native MoE Serving with Bandwidth-Adaptive Execution](https://mlsanity.com/paper/2608.16157/) (2026)
- [SSD-LLaMA: SSD-Native Inference for Trillion-Parameter MoE at 1+ Token/s on a Consumer PC](https://mlsanity.com/paper/2609.18110/) (2026)

## Abstract (arXiv)

The Mixture of Experts (MoE) architecture has emerged as a key technique for scaling Large Language Models by activating only a subset of experts per query. Deploying MoE on consumer-grade edge hardware, however, is constrained by limited device memory, making dynamic expert offloading essential. Unlike prior work that treats offloading purely as a scheduling problem, we leverage expert importance to guide decisions, substituting low-importance activated experts with functionally similar ones already cached in GPU memory, thereby preserving accuracy. As a result, this design reduces memory usage and data transfer, while largely eliminating PCIe overhead. In addition, we introduce a scheduling policy that maximizes the reuse ratio of GPU-cached experts, further boosting efficiency. Extensive evaluations show that our approach delivers 48% lower decoding latency with over 60% expert cache hit rate, while maintaining nearly lossless accuracy.