# MoE-SpeQ: Speculative Quantized Decoding with Proactive Expert Prefetching and Offloading for Mixture-of-Experts

arXiv: https://arxiv.org/abs/2511.14102 · HTML: https://mlsanity.com/paper/2511.14102/

## Key facts

- Cited by 11 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 27 of its 55 references that are in the map.
- First posted on arXiv 18 Nov 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, 27 of 27)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [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)
- [Accelerating Large Language Model Decoding with Speculative Sampling](https://mlsanity.com/paper/2302.01318/) (2023)
- [Phi-4 Technical Report](https://mlsanity.com/paper/2412.08905/) (2024)
- [EAGLE-2: Faster Inference of Language Models with Dynamic Draft Trees](https://mlsanity.com/paper/2406.16858/) (2024)
- [SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression](https://mlsanity.com/paper/2306.03078/) (2023)
- [DistillSpec: Improving Speculative Decoding via Knowledge Distillation](https://mlsanity.com/paper/2310.08461/) (2023)
- [Fast Inference of Mixture-of-Experts Language Models with Offloading](https://mlsanity.com/paper/2312.17238/) (2023)
- [GliDe with a CaPE: A Low-Hassle Method to Accelerate Speculative Decoding](https://mlsanity.com/paper/2402.02082/) (2024)
- [Fiddler: CPU-GPU Orchestration for Fast Inference of Mixture-of-Experts Models](https://mlsanity.com/paper/2402.07033/) (2024)
- [HOBBIT: A Mixed Precision Expert Offloading System for Fast MoE Inference](https://mlsanity.com/paper/2411.01433/) (2024)
- [MoE-Infinity: Efficient MoE Inference on Personal Machines with Sparsity-Aware Expert Cache](https://mlsanity.com/paper/2401.14361/) (2024)
- [A Survey on Inference Optimization Techniques for Mixture of Experts Models](https://mlsanity.com/paper/2412.14219/) (2024)
- [ProMoE: Fast MoE-based LLM Serving using Proactive Caching](https://mlsanity.com/paper/2410.22134/) (2024)
- [Dynamic Speculation Lookahead Accelerates Speculative Decoding of Large Language Models](https://mlsanity.com/paper/2405.04304/) (2024)
- [Dynamic Depth Decoding: Faster Speculative Decoding for LLMs](https://mlsanity.com/paper/2409.00142/) (2024)
- [GRIFFIN: Effective Token Alignment for Faster Speculative Decoding](https://mlsanity.com/paper/2502.11018/) (2025)
- [HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference](https://mlsanity.com/paper/2504.05897/) (2025)
- [TETRIS: Optimal Draft Token Selection for Batch Speculative Decoding](https://mlsanity.com/paper/2502.15197/) (2025)
- [eMoE: Task-aware Memory Efficient Mixture-of-Experts-Based (MoE) Model Inference](https://mlsanity.com/paper/2503.06823/) (2025)
- [CORAL: Learning Consistent Representations across Multi-step Training with Lighter Speculative Drafter](https://mlsanity.com/paper/2502.16880/) (2025)
- [FloE: On-the-Fly MoE Inference on Memory-constrained GPU](https://mlsanity.com/paper/2505.05950/) (2025)
- [SwiftSpec: Ultra-Low Latency LLM Decoding by Scaling Asynchronous Speculative Decoding](https://mlsanity.com/paper/2506.11309/) (2025)
- [FastDraft: How to Train Your Draft](https://mlsanity.com/paper/2411.11055/) (2024)

## Built on by (most cited first, 11 of 11)

- [MoE-SpAc: Efficient MoE Inference Based on Speculative Activation Utility in Heterogeneous Edge Scenarios](https://mlsanity.com/paper/2603.09983/) (2026)
- [PCR: A Prefetch-Enhanced Cache Reuse System for Low-Latency RAG Serving](https://mlsanity.com/paper/2603.23049/) (2026)
- [Less Experts, Faster Decoding: Cost-Aware Speculative Decoding for Mixture-of-Experts](https://mlsanity.com/paper/2607.12696/) (2026)
- [PagedWeight: Efficient MoE LLM Serving with Dynamic Quality-Aware Weight Quantization](https://mlsanity.com/paper/2607.16184/) (2026)
- [DraftExpert: Expansion-Aware Self-Speculative Decoding for End-Device MoE Inference](https://mlsanity.com/paper/2607.24434/) (2026)
- [S2-MoE: Enabling Efficient Self-Speculative Decoding for Mixture-of-Experts on Edge Devices](https://mlsanity.com/paper/2608.15018/) (2026)
- [AcceptMoE: Commitment-Weighted Self-Sizing Verifier Expert Sets for Efficient MoE Speculative Decoding](https://mlsanity.com/paper/2608.02989/) (2026)
- [The Limits of Speculation: Bounding Speculative Decoding in Mixture-of-Experts](https://mlsanity.com/paper/2609.22156/) (2026)
- [ELMoE-3D: Leveraging Intrinsic Elasticity of MoE for Hybrid-Bonding-Enabled Self-Speculative Decoding in On-Premises Serving](https://mlsanity.com/paper/2604.14626/) (2026)
- [SpecPrefetch: Parameter-Efficient Expert Prefetching for Sparse MoE Foundation Models](https://mlsanity.com/paper/2607.24787/) (2026)
- [BigMoMo: Efficient Inference of Large-Scale MoE with Speculative Decoding on Mobile Devices](https://mlsanity.com/paper/2609.14643/) (2026)

## Abstract (arXiv)

The immense memory requirements of state-of-the-art Mixture-of-Experts (MoE) models present a significant challenge for inference, often exceeding the capacity of a single accelerator. While offloading experts to host memory is a common solution, it introduces a severe I/O bottleneck over the PCIe bus, as the data-dependent nature of expert selection places these synchronous transfers directly on the critical path of execution, crippling performance. This paper argues that the I/O bottleneck can be overcome by trading a small amount of cheap, on-device computation to hide the immense cost of data movement. We present MoE-SpeQ, a new inference system built on a novel co-design of speculative execution and expert offloading. MoE-SpeQ employs a small, on-device draft model to predict the sequence of required experts for future tokens. This foresight enables a runtime orchestrator to prefetch these experts from host memory, effectively overlapping the expensive I/O with useful computation and hiding the latency from the critical path. To maximize performance, an adaptive governor, guided by an Amortization Roofline Model, dynamically tunes the speculation strategy to the underlying hardware. Our evaluation on memory-constrained devices shows that for the Phi-MoE model, MoE-SpeQ achieves at most 2.34x speedup over the state-of-the-art offloading framework. Our work establishes a new, principled approach for managing data-dependent memory access in resource-limited environments, making MoE inference more accessible on commodity hardware.