# ZipMoE: Efficient On-Device MoE Serving via Lossless Compression and Cache-Affinity Scheduling

arXiv: https://arxiv.org/abs/2601.21198 · HTML: https://mlsanity.com/paper/2601.21198/

## Key facts

- Cited by 4 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 33 of its 55 references that are in the map.
- First posted on arXiv 29 Jan 2026.

## 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 33)

- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model](https://mlsanity.com/paper/2405.04434/) (2024)
- [LLM-Pruner: On the Structural Pruning of Large Language Models](https://mlsanity.com/paper/2305.11627/) (2023)
- [FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU](https://mlsanity.com/paper/2303.06865/) (2023)
- [DeepSpeed Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scale](https://mlsanity.com/paper/2207.00032/) (2022)
- [A Study of BFLOAT16 for Deep Learning Training](https://mlsanity.com/paper/1905.12322/) (2019)
- [Mobile Edge Intelligence for Large Language Models: A Contemporary Survey](https://mlsanity.com/paper/2407.18921/) (2024)
- [On the Exploitability of Instruction Tuning](https://mlsanity.com/paper/2306.17194/) (2023)
- [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)
- [Quantization Hurts Reasoning? An Empirical Study on Quantized Reasoning Models](https://mlsanity.com/paper/2504.04823/) (2025)
- [Fiddler: CPU-GPU Orchestration for Fast Inference of Mixture-of-Experts Models](https://mlsanity.com/paper/2402.07033/) (2024)
- [EdgeMoE: Empowering Sparse Large Language Models on Mobile Devices](https://mlsanity.com/paper/2308.14352/) (2023)
- [Exploiting LLM Quantization](https://mlsanity.com/paper/2405.18137/) (2024)
- [MoE-Infinity: Efficient MoE Inference on Personal Machines with Sparsity-Aware Expert Cache](https://mlsanity.com/paper/2401.14361/) (2024)
- [ProMoE: Fast MoE-based LLM Serving using Proactive Caching](https://mlsanity.com/paper/2410.22134/) (2024)
- [SiDA-MoE: Sparsity-Inspired Data-Aware Serving for Efficient and Scalable Large Mixture-of-Experts Models](https://mlsanity.com/paper/2310.18859/) (2023)
- ["Give Me BF16 or Give Me Death"? Accuracy-Performance Trade-Offs in LLM Quantization](https://mlsanity.com/paper/2411.02355/) (2024)
- [Prompt, Plan, Perform: LLM-based Humanoid Control via Quantized Imitation Learning](https://mlsanity.com/paper/2309.11359/) (2023)
- [MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design](https://mlsanity.com/paper/2505.05799/) (2025)
- [SwapMoE: Serving Off-the-shelf MoE-based Large Language Models with Tunable Memory Budget](https://mlsanity.com/paper/2308.15030/) (2023)
- [Quantization without Tears](https://mlsanity.com/paper/2411.13918/) (2024)
- [Taming Latency-Memory Trade-Off in MoE-Based LLM Serving via Fine-Grained Expert Offloading](https://mlsanity.com/paper/2502.05370/) (2025)
- [70% Size, 100% Accuracy: Lossless LLM Compression for Efficient GPU Inference via Dynamic-Length Float (DFloat11)](https://mlsanity.com/paper/2504.11651/) (2025)
- [Klotski: Efficient Mixture-of-Expert Inference via Expert-Aware Multi-Batch Pipeline](https://mlsanity.com/paper/2502.06888/) (2025)
- [D2MoE: Dual Routing and Dynamic Scheduling for Efficient On-Device MoE-based LLM Serving](https://mlsanity.com/paper/2504.15299/) (2025)
- [Fine-Tuning, Quantization, and LLMs: Navigating Unintended Outcomes](https://mlsanity.com/paper/2404.04392/) (2024)
- [NeuZip: Memory-Efficient Training and Inference with Dynamic Compression of Neural Networks](https://mlsanity.com/paper/2410.20650/) (2024)
- [ZipNN: Lossless Compression for AI Models](https://mlsanity.com/paper/2411.05239/) (2024)
- [Huff-LLM: End-to-End Lossless Compression for Efficient LLM Inference](https://mlsanity.com/paper/2502.00922/) (2025)

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

- [Lossless Tensor Compression as Program Synthesis](https://mlsanity.com/paper/2608.02162/) (2026)
- [FluxMoE: Decoupling Expert Residency for High-Performance MoE Serving](https://mlsanity.com/paper/2604.02715/) (2026)
- [Beyond Independent Optimization: Compression, MoE Routing, and Quantization Interactions in Multimodal Edge Intelligence](https://mlsanity.com/paper/2607.20981/) (2026)
- [EStream: Fast and Memory-Efficient MoE Prefill through Expert Virtualization on Mobile NPUs](https://mlsanity.com/paper/2609.06551/) (2026)

## Abstract (arXiv)

While Mixture-of-Experts (MoE) architectures substantially bolster the expressive power of large-language models, their prohibitive memory footprint severely impedes the practical deployment on resource-constrained edge devices, especially when model behavior must be preserved without relying on lossy quantization. In this paper, we present ZipMoE, an efficient and semantically lossless on-device MoE serving system. ZipMoE exploits the synergy between the hardware properties of edge devices and the statistical redundancy inherent to MoE parameters via a caching-scheduling co-design with provable performance guarantee. Fundamentally, our design shifts the paradigm of on-device MoE inference from an I/O-bound bottleneck to a compute-centric workflow that enables efficient parallelization. We implement a prototype of ZipMoE and conduct extensive experiments on representative edge computing platforms using popular open-source MoE models and real-world workloads. Our evaluation reveals that ZipMoE achieves up to 72.77% inference latency reduction and up to 6.76× higher throughput than the state-of-the-art systems.Our code is available at: https://github.com/npnothard/ZipMoE-ICML26.