# MiLo: Efficient Quantized MoE Inference with Mixture of Low-Rank Compensators

arXiv: https://arxiv.org/abs/2504.02658 · HTML: https://mlsanity.com/paper/2504.02658/

## Key facts

- Cited by 8 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 26 of its 43 references that are in the map.
- First posted on arXiv 3 Apr 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, 26 of 26)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [PIQA: Reasoning about Physical Commonsense in Natural Language](https://mlsanity.com/paper/1911.11641/) (2019)
- [GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers](https://mlsanity.com/paper/2210.17323/) (2022)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models](https://mlsanity.com/paper/2211.10438/) (2022)
- [AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration](https://mlsanity.com/paper/2306.00978/) (2023)
- [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)
- [Efficient Large-Scale Language Model Training on GPU Clusters Using Megatron-LM](https://mlsanity.com/paper/2104.04473/) (2021)
- [ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformers](https://mlsanity.com/paper/2206.01861/) (2022)
- [DeepSpeed-MoE: Advancing Mixture-of-Experts Inference and Training to Power Next-Generation AI Scale](https://mlsanity.com/paper/2201.05596/) (2022)
- [The case for 4-bit precision: k-bit Inference Scaling Laws](https://mlsanity.com/paper/2212.09720/) (2022)
- [Efficient Large Scale Language Modeling with Mixtures of Experts](https://mlsanity.com/paper/2112.10684/) (2021)
- [ASVD: Activation-aware Singular Value Decomposition for Compressing Large Language Models](https://mlsanity.com/paper/2312.05821/) (2023)
- [Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy](https://mlsanity.com/paper/2310.01334/) (2023)
- [LUT-GEMM: Quantized Matrix Multiplication based on LUTs for Efficient Inference in Large-Scale Generative Language Models](https://mlsanity.com/paper/2206.09557/) (2022)
- [Fast Inference of Mixture-of-Experts Language Models with Offloading](https://mlsanity.com/paper/2312.17238/) (2023)
- [Task-Specific Expert Pruning for Sparse Mixture-of-Experts](https://mlsanity.com/paper/2206.00277/) (2022)
- [Mixture of Quantized Experts (MoQE): Complementary Effect of Low-bit Quantization and Robustness](https://mlsanity.com/paper/2310.02410/) (2023)
- [Who Says Elephants Can't Run: Bringing Large Scale MoE Models into Cloud Scale Production](https://mlsanity.com/paper/2211.10017/) (2022)

## Built on by (most cited first, 8 of 8)

- [PuzzleMoE: Efficient Compression of Large Mixture-of-Experts Models via Sparse Expert Merging and Bit-packed inference](https://mlsanity.com/paper/2511.04805/) (2025)
- [PagedWeight: Efficient MoE LLM Serving with Dynamic Quality-Aware Weight Quantization](https://mlsanity.com/paper/2607.16184/) (2026)
- [MoE-Compression: How the Compression Error of Experts Affects the Inference Accuracy of MoE Model?](https://mlsanity.com/paper/2509.07727/) (2025)
- [TileQ: Efficient Low-Rank Quantization of Mixture-of-Experts with 2D Tiling](https://mlsanity.com/paper/2605.09281/) (2026)
- [BitsMoE: Efficient Spectral Energy-Guided Bit Allocation for MoE LLM Quantization](https://mlsanity.com/paper/2606.00079/) (2026)
- [Every Expert Counts: ExactMoE for Memory-Efficient W4A16 Inference](https://mlsanity.com/paper/2608.15383/) (2026)
- [ITC-MoE: Importance-guided Token-aware Compression for MoE Diffusion Language Models](https://mlsanity.com/paper/2610.01296/) (2026)
- [DuoRate: Two-Rate Per-Expert Precision Allocation for Mixture-of-Experts Serving](https://mlsanity.com/paper/2610.13328/) (2026)

## Abstract (arXiv)

A critical approach for efficiently deploying Mixture-of-Experts (MoE) models with massive parameters is quantization. However, state-of-the-art MoE models suffer from non-negligible accuracy loss with extreme quantization, such as under 4 bits. To address this, we introduce MiLo, a novel method that augments highly quantized MoEs with a mixture of low-rank compensators. These compensators consume only a small amount of additional memory but significantly recover accuracy loss from extreme quantization. MiLo also identifies that MoEmodels exhibit distinctive characteristics across weights due to their hybrid dense-sparse architectures, and employs adaptive rank selection policies along with iterative optimizations to close the accuracy gap. MiLo does not rely on calibration data, allowing it to generalize to different MoE models and datasets without overfitting to a calibration set. To avoid the hardware inefficiencies of extreme quantization, such as 3-bit, MiLo develops Tensor Core-friendly 3-bit kernels, enabling measured latency speedups on 3-bit quantized MoE models. Our evaluation shows that MiLo outperforms existing methods on SoTA MoE models across various tasks.