Less Experts, Faster Decoding: Cost-Aware Speculative Decoding for Mixture-of-Experts

• URL: http://arxiv.org/abs/2607.12696v1
• Date: Tue, 14 Jul 2026 12:22:55 GMT
• Title: Less Experts, Faster Decoding: Cost-Aware Speculative Decoding for Mixture-of-Experts
• Abstract summary: We propose a cost-aware speculative decoding framework that incorporates predicted marginal expert activation cost into draft selection.<n>We evaluate textscEcoSpec on three large-scale MoE models, including DeepSeek-V3.1 (671B), Qwen3-235B-A22B, and GPT-OSS-120B.
• Score: 34.20364644493512
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Sparse Mixture-of-Experts (MoE) models have become an important approach for scaling Large Language Models (LLMs), but their inference efficiency depends strongly on expert activation patterns. Speculative decoding (SD) accelerates autoregressive generation by verifying multiple draft tokens in parallel, yet existing draft selection strategies primarily optimize acceptance likelihood. In large-scale MoE models, however, selecting draft tokens also determines the union of experts activated during verification. We observe that confidence-driven SD can introduce \textit{expert scattering}: high-probability draft tokens may route to disjoint experts, increasing expert-weight memory traffic and reducing the speedup from speculation. Motivated by this observation, we revisit draft-tree selection under the non-uniform memory-cost structure of MoE inference. We propose \textsc{EcoSpec}, a cost-aware speculative decoding framework that incorporates predicted marginal expert activation cost into draft selection. With a lightweight expert predictor and a dynamic expert buffer, \textsc{EcoSpec} favors draft paths that preserve high acceptance likelihood while reusing experts already covered by the current verification set, without modifying the target-model verification rule. We evaluate \textsc{EcoSpec} on three large-scale MoE models, including DeepSeek-V3.1 (671B), Qwen3-235B-A22B, and GPT-OSS-120B, across reasoning, coding, question-answering, and dialogue benchmarks. \textsc{EcoSpec} consistently reduces active expert footprints and improves end-to-end decoding speed, achieving up to $1.62\times$ speedup. These results show that accounting for expert activation cost is important for efficient speculative decoding in large-scale MoE models.

Related papers

• AnchorMoE: Interpretable Time Series Classification via Anchor-Routed MoE [51.994752158953084]
  AnchorMoE is an interpretable-by-construction classification framework.<n>It encodes multi-view representations of local patches and routes them to specialized experts.<n>Experiments on real-world and synthetic benchmarks demonstrate that AnchorMoE achieves highly competitive classification performance.
  arXiv  Detail & Related papers  (2026-06-02T13:30:54Z)
• Hybrid Verified Decoding: Learning to Allocate Verification in Speculative Decoding [8.297861366384156]
  Hybrid Verified Decoding predicts the accepted length of a cache draft before verification.<n>Our analysis shows how prompt structure creates cache opportunities, how high-payoff cache drafts concentrate in a small part of the draft space, and how payoff-guided selection reduces sequential decoding draft selection.
  arXiv  Detail & Related papers  (2026-05-31T05:22:40Z)
• Making Every Verified Token Count: Adaptive Verification for MoE Speculative Decoding [15.040000425985324]
  Tree-based speculative decoding accelerates autoregressive generation by verifying multiple draft candidates in parallel, but this advantage weakens for sparse Mixture-of-Experts (MoE) models.<n>We propose EVICT, a training-free, hyper parameter-free, and lossless adaptive verification method for MoE speculative decoding.<n> EVICT makes every verified token count by truncating the draft tree before target verification and retaining only the cost-effective prefix.
  arXiv  Detail & Related papers  (2026-05-01T01:52:01Z)
• MoE-Spec: Expert Budgeting for Efficient Speculative Decoding [4.064682810747041]
  We propose a training-free verification-time expert budgeting method that decouples speculation depth from memory cost.<n>Experiments across multiple model scales and datasets show that this method yields 10--30% higher throughput than state-of-the-art speculative decoding baselines.
  arXiv  Detail & Related papers  (2026-02-17T22:02:36Z)
• TriSpec: Ternary Speculative Decoding via Lightweight Proxy Verification [63.65902785448346]
  Speculative decoding offers significant speed-ups through its lightweight drafting and parallel verification mechanism.<n>We propose TriSpec, a novel ternary SD framework that introduces a lightweight proxy to significantly reduce computational cost.<n>Experiments on the Qwen3 and DeepSeek-R1-Distill-Qwen/LLaMA families show that TriSpec achieves up to 35% speedup over standard SD.
  arXiv  Detail & Related papers  (2026-01-30T17:04:18Z)
• Accelerate Speculative Decoding with Sparse Computation in Verification [49.74839681322316]
  Speculative decoding accelerates autoregressive language model inference by verifying multiple draft tokens in parallel.<n>Existing sparsification methods are designed primarily for standard token-by-token autoregressive decoding.<n>We propose a sparse verification framework that jointly sparsifies attention, FFN, and MoE components during the verification stage to reduce the dominant computation cost.
  arXiv  Detail & Related papers  (2025-12-26T07:53:41Z)
• Beyond Redundancy: Diverse and Specialized Multi-Expert Sparse Autoencoder [59.89996751196727]
  Sparse autoencoders (SAEs) have emerged as a powerful tool for interpreting large language models.<n>SAEs' hidden layers have high dimensionality to satisfy sparsity constraints, resulting in prohibitive training and inference costs.<n>Recent Mixture of Experts (MoE) approaches attempt to address this by SAEs into narrower expert networks with gated activation.<n>We propose two key innovations: (1) Multiple Expert Activation that simultaneously engages semantically weighted expert subsets to encourage specialization, and (2) Feature Scaling that enhances diversity through adaptive high-frequency scaling.
  arXiv  Detail & Related papers  (2025-11-07T22:19:34Z)
• When, What, and How: Rethinking Retrieval-Enhanced Speculative Decoding [29.402164743559]
  ReSpec is a novel framework that transforms drafter switching into adaptive decision-making.<n>Experiments on Spec-Bench demonstrate that ReSpec state-of-the-art acceleration achieves over $33%$ and $25%$, respectively.
  arXiv  Detail & Related papers  (2025-11-03T06:57:16Z)
• Unified Sparse Mixture of Experts [14.774596844618396]
  Sparse Mixture of Experts (SMoEs) models scale the capacity of models while maintaining constant computational overhead.<n>This paper proposes a Unified Sparse Mixture of Experts (USMoE) framework that addresses these limitations.
  arXiv  Detail & Related papers  (2025-03-29T07:15:12Z)
• 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)
• Mixture Compressor for Mixture-of-Experts LLMs Gains More [71.0473038084673]
  We propose a training-free Mixture-Compressor for Mixture-of-Experts large language models (MoE-LLMs)<n>Our MC integrates static quantization and dynamic pruning to collaboratively achieve extreme compression for MoE-LLMs with less accuracy loss.<n>For instance, at 2.54 bits, MC compresses 76.6% of the model, with only a 3.8% average accuracy loss.
  arXiv  Detail & Related papers  (2024-10-08T18:09:38Z)
• Multilinear Mixture of Experts: Scalable Expert Specialization through Factorization [51.98792406392873]
  Mixture of Experts (MoE) provides a powerful way to decompose dense layers into smaller, modular computations. A major challenge lies in the computational cost of scaling the number of experts high enough to achieve fine-grained specialization. We propose the Multilinear Mixture of Experts ($mu$MoE) layer to address this, focusing on vision models.
  arXiv  Detail & Related papers  (2024-02-19T21:20:22Z)

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.