Speculative MoE: Communication Efficient Parallel MoE Inference with Speculative Token and Expert Pre-scheduling

• URL: http://arxiv.org/abs/2503.04398v3
• Date: Wed, 19 Mar 2025 02:03:39 GMT
• Title: Speculative MoE: Communication Efficient Parallel MoE Inference with Speculative Token and Expert Pre-scheduling
• Authors: Yan Li, Pengfei Zheng, Shuang Chen, Zewei Xu, Yuanhao Lai, Yunfei Du, Zhengang Wang,
• Abstract summary: MoE (Mixture of Experts) prevails as a neural architecture that can scale modern transformer-based LLMs (Large Language Models) to unprecedented scales.<n>DeepSpeed-MoE, one state-of-the-art MoE inference framework, adopts a 3D-parallel paradigm including EP (Expert Parallelism), TP (Tensor Parallel) and DP (Data Parallelism)<n>Our work aims to boost DeepSpeed-MoE by strategically reducing EP's communication overhead with a technique named Speculative MoE.
• Score: 3.529891364583952
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: MoE (Mixture of Experts) prevails as a neural architecture that can scale modern transformer-based LLMs (Large Language Models) to unprecedented scales. Nevertheless, large MoEs' great demands of computing power, memory capacity and memory bandwidth make scalable serving a fundamental challenge and efficient parallel inference has become a requisite to attain adequate throughput under latency constraints. DeepSpeed-MoE, one state-of-the-art MoE inference framework, adopts a 3D-parallel paradigm including EP (Expert Parallelism), TP (Tensor Parallel) and DP (Data Parallelism). However, our analysis shows DeepSpeed-MoE's inference efficiency is largely bottlenecked by EP, which is implemented with costly all-to-all collectives to route token activation. Our work aims to boost DeepSpeed-MoE by strategically reducing EP's communication overhead with a technique named Speculative MoE. Speculative MoE has two speculative parallelization schemes, speculative token shuffling and speculative expert grouping, which predict outstanding tokens' expert routing paths and pre-schedule tokens and experts across devices to losslessly trim EP's communication volume. Besides DeepSpeed-MoE, we also build Speculative MoE into a prevailing MoE inference engine SGLang. Experiments show Speculative MoE can significantly boost state-of-the-art MoE inference frameworks on fast homogeneous and slow heterogeneous interconnects.

Related papers

• Multi-Head LatentMoE and Head Parallel: Communication-Efficient and Deterministic MoE Parallelism [7.862911132148511]
  Multi-Head LatentMoE and Head Parallel achieve $O(1)$ communication cost regardless of $k$, completely balanced traffic, and deterministic communication.<n>Compared to MoE with EP, Multi-Head LatentMoE with HP trains up to $1.61times$ faster while having identical performance.
  arXiv  Detail & Related papers  (2026-02-04T18:57:19Z)
• ZipMoE: Efficient On-Device MoE Serving via Lossless Compression and Cache-Affinity Scheduling [56.88966608455977]
  ZipMoE exploits the synergy between the hardware properties of edge devices and the statistical redundancy inherent to MoE parameters.<n>ZipMoE achieves up to $72.77%$ inference latency reduction and up to $6.76times$ higher throughput than the state-of-the-art systems.
  arXiv  Detail & Related papers  (2026-01-29T02:51:59Z)
• Least-Loaded Expert Parallelism: Load Balancing An Imbalanced Mixture-of-Experts [74.40169987564724]
  Expert parallelism (EP) is designed to scale MoE models by distributing experts across multiple devices.<n>Under extreme imbalance, EP can funnel a disproportionate number of tokens to a small number of experts, leading to compute- and memory-bound failures.<n>We propose Least-Loaded Expert Parallelism (LLEP), a novel EP algorithm that dynamically reroutes excess tokens and associated expert parameters from overloaded devices to underutilized ones.
  arXiv  Detail & Related papers  (2026-01-23T18:19:15Z)
• MoE-SpeQ: Speculative Quantized Decoding with Proactive Expert Prefetching and Offloading for Mixture-of-Experts [29.437264687850874]
  We present MoE-SpeQ, a new inference system built on a novel co-design of speculative execution and expert offloading.<n>MoE-SpeQ employs a small, on-device draft model to predict the sequence of required experts for future tokens.<n>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.
  arXiv  Detail & Related papers  (2025-11-18T03:40:19Z)
• Pangu Embedded: An Efficient Dual-system LLM Reasoner with Metacognition [95.54406667705999]
  Pangu Embedded is an efficient Large Language Model (LLM) reasoner developed on Ascend Neural Processing Units (NPUs)<n>It addresses the significant computational costs and inference latency challenges prevalent in existing reasoning-optimized LLMs.<n>It delivers rapid responses and state-of-the-art reasoning quality within a single, unified model architecture.
  arXiv  Detail & Related papers  (2025-05-28T14:03:02Z)
• Accelerating MoE Model Inference with Expert Sharding [1.4733737463429546]
  Mixture of experts (MoE) models achieve state-of-the-art results in language modeling but suffer from inefficient hardware utilization due to imbalanced token routing and communication overhead. We introduce MoEShard, an inference system that achieves perfect load balancing through tensor sharding of MoE experts.
  arXiv  Detail & Related papers  (2025-03-11T14:15:01Z)
• Mixture of Cache-Conditional Experts for Efficient Mobile Device Inference [14.57414071160821]
  We introduce a novel cache-aware routing strategy that leverages expert reuse during token generation to improve cache locality.<n>We present on-device results demonstrating 2$times$ speedups on mobile devices.
  arXiv  Detail & Related papers  (2024-11-27T18:59:48Z)
• WDMoE: Wireless Distributed Mixture of Experts for Large Language Models [68.45482959423323]
  Large Language Models (LLMs) have achieved significant success in various natural language processing tasks. We propose a wireless distributed Mixture of Experts (WDMoE) architecture to enable collaborative deployment of LLMs across edge servers at the base station (BS) and mobile devices in wireless networks.
  arXiv  Detail & Related papers  (2024-11-11T02:48:00Z)
• HOBBIT: A Mixed Precision Expert Offloading System for Fast MoE Inference [54.40808356999408]
  We present HOBBIT, a mixed precision expert offloading system to enable flexible and efficient MoE inference. Our key insight is that dynamically replacing less critical cache-miss experts with low precision versions can substantially reduce expert-loading latency. HOBBIT achieves up to a 9.93x speedup in decoding compared to state-of-the-art MoE offloading systems.
  arXiv  Detail & Related papers  (2024-11-03T04:25:46Z)
• Read-ME: Refactorizing LLMs as Router-Decoupled Mixture of Experts with System Co-Design [59.00758127310582]
  We propose a novel framework Read-ME that transforms pre-trained dense LLMs into smaller MoE models. Our approach employs activation sparsity to extract experts. Read-ME outperforms other popular open-source dense models of similar scales.
  arXiv  Detail & Related papers  (2024-10-24T19:48:51Z)
• EPS-MoE: Expert Pipeline Scheduler for Cost-Efficient MoE Inference [49.94169109038806]
  This paper introduces EPS-MoE, a novel expert pipeline scheduler for MoE that surpasses the existing parallelism schemes.<n>Our results demonstrate at most 52.4% improvement in prefill throughput compared to existing parallel inference methods.
  arXiv  Detail & Related papers  (2024-10-16T05:17:49Z)
• Shortcut-connected Expert Parallelism for Accelerating Mixture-of-Experts [4.629608387540524]
  ScMoE is a novel shortcut-connected MoE architecture integrated with an overlapping parallelization strategy.<n>Compared to the prevalent top-2 MoE baseline, ScMoE achieves speedups of 1.49 times in training and 1.82 times in inference.
  arXiv  Detail & Related papers  (2024-04-07T17:17:23Z)
• Pipeline MoE: A Flexible MoE Implementation with Pipeline Parallelism [91.9372563527801]
  Existing MoE models suffer from tremendous inner-node and inter-node communication overhead. We propose a novel MoE architecture called Pipeline MoE (PPMoE) to tackle them. PPMoE builds expert parallel incorporating with tensor parallel and replaces communication-intensive all-to-all dispatching and gathering.
  arXiv  Detail & Related papers  (2023-04-22T14:09:14Z)
• Task-Specific Expert Pruning for Sparse Mixture-of-Experts [105.20605021416276]
  Mixture-of-Experts (MoE) model is powerful for large-scale pre-training. MoE is hard to be deployed on cloud or mobile environment. We propose a general method to progressively drop the non-professional experts for the target downstream task.
  arXiv  Detail & Related papers  (2022-06-01T07:09:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.