# DuoRate: Two-Rate Per-Expert Precision Allocation for Mixture-of-Experts Serving

arXiv: https://arxiv.org/abs/2610.13328 · HTML: https://mlsanity.com/paper/2610.13328/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Expert routing strategies, one of 12 directions in Mixture-of-experts.
- Builds on 38 of its 43 references that are in the map.
- First posted on arXiv 9 Oct 2026.

## Placed in

- Mixture-of-experts / [Expert routing strategies](https://mlsanity.com/moe/expert-routing-strategies/)

## Builds on (most cited first, 30 of 38)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers](https://mlsanity.com/paper/2210.17323/) (2022)
- [SqueezeLLM: Dense-and-Sparse Quantization](https://mlsanity.com/paper/2306.07629/) (2023)
- [HAWQ-V2: Hessian Aware trace-Weighted Quantization of Neural Networks](https://mlsanity.com/paper/1911.03852/) (2019)
- [EdgeMoE: Empowering Sparse Large Language Models on Mobile Devices](https://mlsanity.com/paper/2308.14352/) (2023)
- [HOBBIT: A Mixed Precision Expert Offloading System for Fast MoE Inference](https://mlsanity.com/paper/2411.01433/) (2024)
- [Any-Precision LLM: Low-Cost Deployment of Multiple, Different-Sized LLMs](https://mlsanity.com/paper/2402.10517/) (2024)
- [Mixture Compressor for Mixture-of-Experts LLMs Gains More](https://mlsanity.com/paper/2410.06270/) (2024)
- [MoEQuant: Enhancing Quantization for Mixture-of-Experts Large Language Models via Expert-Balanced Sampling and Affinity Guidance](https://mlsanity.com/paper/2505.03804/) (2025)
- [Accuracy is Not All You Need](https://mlsanity.com/paper/2407.09141/) (2024)
- [MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design](https://mlsanity.com/paper/2505.05799/) (2025)
- [D2MoE: Dual Routing and Dynamic Scheduling for Efficient On-Device MoE-based LLM Serving](https://mlsanity.com/paper/2504.15299/) (2025)
- [Progressive Mixed-Precision Decoding for Efficient LLM Inference](https://mlsanity.com/paper/2410.13461/) (2024)
- [Matryoshka Quantization](https://mlsanity.com/paper/2502.06786/) (2025)
- [HiFloat4 Format for Language Model Inference](https://mlsanity.com/paper/2602.11287/) (2026)
- [AnyBCQ: Hardware Efficient Flexible Binary-Coded Quantization for Multi-Precision LLMs](https://mlsanity.com/paper/2510.10467/) (2025)
- [MiLo: Efficient Quantized MoE Inference with Mixture of Low-Rank Compensators](https://mlsanity.com/paper/2504.02658/) (2025)
- [Dynamic Expert Quantization for Scalable Mixture-of-Experts Inference](https://mlsanity.com/paper/2511.15015/) (2025)
- [GEMQ: Global Expert-Level Mixed-Precision Quantization for MoE LLMs](https://mlsanity.com/paper/2605.23078/) (2026)
- [AlphaQ: Calibration-Free Bit Allocation for Mixture-of-Experts Quantization](https://mlsanity.com/paper/2606.04980/) (2026)
- [Radio: Rate-Distortion Optimization for Large Language Model Compression](https://mlsanity.com/paper/2505.03031/) (2025)
- [MoPEQ: Mixture of Mixed Precision Quantized Experts](https://mlsanity.com/paper/2509.02512/) (2025)
- [DuoServe-MoE: Dual-Phase Expert Prefetch and Caching for LLM Inference QoS Assurance](https://mlsanity.com/paper/2509.07379/) (2025)
- [From Tokens to Layers: Redefining Stall-Free Scheduling for MoE Serving with Layered Prefill](https://mlsanity.com/paper/2510.08055/) (2025)
- [Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs](https://mlsanity.com/paper/2605.20315/) (2026)
- [SliceMoE: Bit-Sliced Expert Caching under Miss-Rate Constraints for Efficient MoE Inference](https://mlsanity.com/paper/2512.12990/) (2025)
- [RateQuant: Optimal Mixed-Precision KV Cache Quantization via Rate-Distortion Theory](https://mlsanity.com/paper/2605.06675/) (2026)

## Abstract (arXiv)

Serving a Mixture-of-Experts (MoE) model pays for expert precision twice: the resident footprint pays for every expert the router can reach, while each batch-one decode step pays only for the experts it selects. These are two different rate functionals over the same per-expert widths, yet published per-expert MoE allocators constrain only the first. We call the difference the store-read gap; in the released BitsMoE checkpoint, 2.54 bits per weight (bpw) of storage become 7.50 bpw of decode traffic. We propose DuoRate, which stores once and reads per workload. Offline, it stores one uniform tier of a prefix-readable weight stream and bakes a distortion tensor. Online, it profiles a workload's own prefill without labels and solves a Lagrangian rate-distortion allocation under the decode functional; routing frequency provably cancels from every per-expert decision, and the solve costs one dot product per expert and a bisection. A deployment therefore keeps a single artifact that prefill reads at the stored rate and decode reads at the workload's own rate. On Qwen3-30B-A3B, DuoRate reading 2.3 bpw exceeds every 2-bit-class baseline by 6.3 to 47.0 points of average accuracy, and at 2.9 bpw it matches 4-bit formats that read 1.4-1.6 bpw more. The advantage is largest under long decoding: on GSM8K, DuoRate at 2.9 bpw matches or exceeds every 4-bit format and trails BF16 by only 0.25 points, and at 2.6 bpw it still matches or exceeds the 4.5-bit NF4 and FP4. Against controls in its own format, the allocation alone is worth 0.07-0.11 bpw of read rate. Code will be released upon publication.