# SwapMoE: Serving Off-the-shelf MoE-based Large Language Models with Tunable Memory Budget

arXiv: https://arxiv.org/abs/2308.15030 · HTML: https://mlsanity.com/paper/2308.15030/

## Key facts

- Cited by 27 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 19 of its 36 references that are in the map.
- First posted on arXiv 29 Aug 2023.

## Placed in

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

## Builds on (most cited first, 19 of 19)

- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [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)
- [HuggingFace's Transformers: State-of-the-art Natural Language Processing](https://mlsanity.com/paper/1910.03771/) (2019)
- [GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding](https://mlsanity.com/paper/2006.16668/) (2020)
- [Efficient Large Scale Language Modeling with Mixtures of Experts](https://mlsanity.com/paper/2112.10684/) (2021)
- [MoEfication: Transformer Feed-forward Layers are Mixtures of Experts](https://mlsanity.com/paper/2110.01786/) (2021)
- [M3ViT: Mixture-of-Experts Vision Transformer for Efficient Multi-task Learning with Model-Accelerator Co-design](https://mlsanity.com/paper/2210.14793/) (2022)
- [Beyond Distillation: Task-level Mixture-of-Experts for Efficient Inference](https://mlsanity.com/paper/2110.03742/) (2021)
- [Scalable and Efficient MoE Training for Multitask Multilingual Models](https://mlsanity.com/paper/2109.10465/) (2021)
- [Task-Specific Expert Pruning for Sparse Mixture-of-Experts](https://mlsanity.com/paper/2206.00277/) (2022)
- [NestDNN: Resource-Aware Multi-Tenant On-Device Deep Learning for Continuous Mobile Vision](https://mlsanity.com/paper/1810.10090/) (2018)
- [MoESys: A Distributed and Efficient Mixture-of-Experts Training and Inference System for Internet Services](https://mlsanity.com/paper/2205.10034/) (2022)
- [Towards MoE Deployment: Mitigating Inefficiencies in Mixture-of-Expert (MoE) Inference](https://mlsanity.com/paper/2303.06182/) (2023)
- [LegoDNN: Block-grained Scaling of Deep Neural Networks for Mobile Vision](https://mlsanity.com/paper/2112.09852/) (2021)
- [AdaptiveNet: Post-deployment Neural Architecture Adaptation for Diverse Edge Environments](https://mlsanity.com/paper/2303.07129/) (2023)
- [Dynamic Slicing for Deep Neural Networks](https://mlsanity.com/paper/2009.13747/) (2020)
- [Cost-effective On-device Continual Learning over Memory Hierarchy with Miro](https://mlsanity.com/paper/2308.06053/) (2023)

## Built on by (most cited first, 27 of 27)

- [A Survey of Resource-efficient LLM and Multimodal Foundation Models](https://mlsanity.com/paper/2401.08092/) (2024)
- [ProMoE: Fast MoE-based LLM Serving using Proactive Caching](https://mlsanity.com/paper/2410.22134/) (2024)
- [Large Model Based Agents: State-of-the-Art, Cooperation Paradigms, Security and Privacy, and Future Trends](https://mlsanity.com/paper/2409.14457/) (2024)
- [Taming Latency-Memory Trade-Off in MoE-Based LLM Serving via Fine-Grained Expert Offloading](https://mlsanity.com/paper/2502.05370/) (2025)
- [DART: Diffusion-Inspired Speculative Decoding for Fast LLM Inference](https://mlsanity.com/paper/2601.19278/) (2026)
- [Mixture of Cache-Conditional Experts for Efficient Mobile Device Inference](https://mlsanity.com/paper/2412.00099/) (2024)
- [GRACE-MoE: Grouping and Replication with Locality-Aware Routing for Efficient Distributed MoE Inference](https://mlsanity.com/paper/2509.25041/) (2025)
- [ResMoE: Space-efficient Compression of Mixture of Experts LLMs via Residual Restoration](https://mlsanity.com/paper/2503.06881/) (2025)
- [Not All Models Suit Expert Offloading: On Local Routing Consistency of Mixture-of-Expert Models](https://mlsanity.com/paper/2505.16056/) (2025)
- [Accelerating Edge Inference for Distributed MoE Models with Latency-Optimized Expert Placement](https://mlsanity.com/paper/2508.12851/) (2025)
- [Dynamic Expert Quantization for Scalable Mixture-of-Experts Inference](https://mlsanity.com/paper/2511.15015/) (2025)
- [CoServe: Efficient Collaboration-of-Experts (CoE) Model Inference with Limited Memory](https://mlsanity.com/paper/2503.02354/) (2025)
- [DuoServe-MoE: Dual-Phase Expert Prefetch and Caching for LLM Inference QoS Assurance](https://mlsanity.com/paper/2509.07379/) (2025)
- [BuddyMoE: Exploiting Expert Redundancy to Accelerate Memory-Constrained Mixture-of-Experts Inference](https://mlsanity.com/paper/2511.10054/) (2025)
- [ZipMoE: Efficient On-Device MoE Serving via Lossless Compression and Cache-Affinity Scheduling](https://mlsanity.com/paper/2601.21198/) (2026)
- [Efficient Deployment of Vision-Language Models on Mobile Devices: A Case Study on OnePlus 13R](https://mlsanity.com/paper/2507.08505/) (2025)
- [CoMoE: Collaborative Optimization of Expert Aggregation and Offloading for MoE-based LLMs at Edge](https://mlsanity.com/paper/2508.09208/) (2025)
- [Adaptive and Resource-efficient Agentic AI Systems for Mobile and Embedded Devices: A Survey](https://mlsanity.com/paper/2510.00078/) (2025)
- [MoE-Prefill: Zero Redundancy Overheads in MoE Prefill Serving](https://mlsanity.com/paper/2605.02960/) (2026)
- [Federated Fine-Tuning of Sparsely-Activated Large Language Models on Resource-Constrained Devices](https://mlsanity.com/paper/2508.19078/) (2025)
- [MoE-Compression: How the Compression Error of Experts Affects the Inference Accuracy of MoE Model?](https://mlsanity.com/paper/2509.07727/) (2025)
- [Efficient CPU-GPU Collaborative Inference for MoE-based LLMs on Memory-Limited Systems](https://mlsanity.com/paper/2512.16473/) (2025)
- [A Replicate-and-Quantize Strategy for Plug-and-Play Load Balancing of Sparse Mixture-of-Experts LLMs](https://mlsanity.com/paper/2602.19938/) (2026)
- [Networking-Aware Energy Efficiency in Agentic AI Inference: A Survey](https://mlsanity.com/paper/2604.07857/) (2026)
- [VisMMOE: Exploiting Visual-Expert Affinity for Efficient Visual-Language MoE Offloading](https://mlsanity.com/paper/2605.05899/) (2026)
- [Every Expert Counts: ExactMoE for Memory-Efficient W4A16 Inference](https://mlsanity.com/paper/2608.15383/) (2026)
- [MaskCoFT: Masked Co-Adaptive Fine-Tuning for Memory-Efficient MoE Inference](https://mlsanity.com/paper/2609.34077/) (2026)

## Abstract (arXiv)

Mixture of experts (MoE) is a popular technique to improve capacity of Large Language Models (LLMs) with conditionally-activated parallel experts. However, serving MoE models on memory-constrained devices is challenging due to the large parameter size. Typical solutions such as memory swapping or expert pruning may lead to significantly higher latency or severe accuracy loss. In this paper, we introduce SwapMoE, a framework for efficient serving of MoE-based large language models with tunable memory budgets. The main idea of SwapMoE is to keep a small dynamic set of important experts, namely Virtual Experts, in the main memory for inference, while seamlessly maintaining how the Virtual Experts map to the actual experts. Experiments have shown that SwapMoE can reduce the memory footprint while maintaining reasonable accuracy. For example, on text summarization tasks with Switch Transformer, SwapMoE can reduce the memory consumption from 14.2 GiB to 4.7 GiB, together with 50% latency reduction and a slight Rouge-2 score drop of 0.041.