WhiFlash: Accelerating Speculative Decoding with Token-Level Cross-Paradigm Routing

• URL: http://arxiv.org/abs/2606.07710v1
• Date: Fri, 05 Jun 2026 13:23:33 GMT
• Title: WhiFlash: Accelerating Speculative Decoding with Token-Level Cross-Paradigm Routing
• Abstract summary: WhiFlash is a cross-paradigm SD method that unifies autoregressive and diffusion-based parallel drafting under a single token-level controller.<n>We show that WhiFlash achieves significantly higher acceptance lengths, yielding category-specific throughput gains of up to 69.6%.
• Score: 44.656073829954636
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The autoregressive nature of large language models (LLMs) remains a significant bottleneck for inference, particularly in complex agentic workloads. While speculative decoding (SD) accelerates inference, current approaches rely on static drafting paradigms, utilising either autoregressive drafting models for reasoning or diffusion-based parallel drafting models for structured outputs. We empirically find that drafting accuracy fluctuates dramatically within a single sequence, leaving significant performance unrealised by static paradigms and coarse-grained routing. To address this volatility, we introduce WhiFlash, the first cross-paradigm SD method that unifies autoregressive and diffusion-based parallel drafting under a single token-level controller. WhiFlash adopts a fine-grained routing mechanism that employs either a lightweight entropy-based or a learned neural policy, both parametrised to provide a tunable balance between expected token gain and latency. To make high-frequency switching computationally viable, we introduce novel cache-management optimisations, Lazy Catch-up and KV-only Prefill, reducing switching overhead to below 7% of per-round latency. By capitalising on the complementary strengths of fundamentally distinct drafting architectures, WhiFlash achieves significantly higher acceptance lengths, yielding category-specific throughput gains of up to 69.6% over the state-of-the-art autoregressive EAGLE-3 and 37.3% over the diffusion-based DFlash.

Related papers

• WAM-Diff2: Hierarchical AR-to-Diffusion Distillation for Highly Efficient Autonomous Driving VLA [27.102605117827398]
  Vision-Language-Action (VLA) models have emerged as a prominent paradigm for end-to-end autonomous driving.<n>They are constrained by high computational latency and exposure bias arising from sequential autoregressive decoding.<n>We introduce WAM-Diff2, a multi-task discrete diffusion VLA framework powered by a three-stage hierarchical strategy.
  arXiv  Detail & Related papers  (2026-08-02T06:45:16Z)
• AdaFlash: Adaptive Speculative Decoding via On-Policy Distilled Diffusion Drafters [67.51886052453452]
  Speculative decoding has become a prevalent paradigm for accelerating large language model inference.<n>Recent work such as DFlash further boosts drafting efficiency by leveraging diffusion drafters.<n>We propose AdaFlash framework, comprising two components: (i) an on-policy distillation (OPD) algorithm with reverse-KL divergence tailored for diffusion drafters, and (ii) an adaptive length head that dynamically adjusts the candidate sequence length on the fly.
  arXiv  Detail & Related papers  (2026-07-21T15:52:50Z)
• Relative Kinetic Utility for Reasoning-Aware Structural Pruning in Large Language Models [0.0]
  We propose a novel framework that elevates discrete pruning to a continuous kinetic integral over the depth manifold of a model.<n>Experiments on Qwen-2.5-7B and LLaMA-3-8B improve performance in the high-sparsity regime around 40%.<n>RKU attains 13.34% accuracy on GSM8K at 40% sparsity, outperforming the strongest baseline.
  arXiv  Detail & Related papers  (2026-05-09T15:47:53Z)
• DFlash: Block Diffusion for Flash Speculative Decoding [11.98141750480807]
  Autoregressive large language models (LLMs) deliver strong performance but require inherently sequential decoding.<n>We introduce DFlash, a speculative decoding framework that employs a lightweight block diffusion model for parallel drafting.
  arXiv  Detail & Related papers  (2026-02-05T18:59:30Z)
• Causal Autoregressive Diffusion Language Model [70.7353007255797]
  CARD reformulates the diffusion process within a strictly causal attention mask, enabling dense, per-token supervision in a single forward pass.<n>Our results demonstrate that CARD achieves ARM-level data efficiency while unlocking the latency benefits of parallel generation.
  arXiv  Detail & Related papers  (2026-01-29T17:38:29Z)
• Fast-ARDiff: An Entropy-informed Acceleration Framework for Continuous Space Autoregressive Generation [12.384836052394272]
  Autoregressive(AR)-diffusion hybrid paradigms combine AR's structured modeling with diffusion's synthesis.<n>We propose a unified AR-diffusion framework Fast-ARDiff that jointly optimize both components.<n>Fast-ARDiff achieves state-of-the-art acceleration across diverse models.
  arXiv  Detail & Related papers  (2025-12-09T12:35:18Z)
• Beyond Confidence: Adaptive and Coherent Decoding for Diffusion Language Models [64.92045568376705]
  Coherent Contextual Decoding (CCD) is a novel inference framework built upon two core innovations.<n>CCD employs a trajectory rectification mechanism that leverages historical context to enhance sequence coherence.<n>Instead of rigid allocations based on diffusion steps, we introduce an adaptive sampling strategy that dynamically adjusts the unmasking budget for each step.
  arXiv  Detail & Related papers  (2025-11-26T09:49:48Z)
• SDAR: A Synergistic Diffusion-AutoRegression Paradigm for Scalable Sequence Generation [62.14510717860079]
  We propose a Synergistic Diffusion-Autoregression paradigm that unifies the training efficiency of autoregressive models with the parallel inference capability of diffusion.<n>SDAR performs a lightweight paradigm conversion that transforms a well-trained autoregressive (AR) model into a blockwise diffusion model through brief, data-efficient adaptation.<n>Building on this insight, SDAR achieves efficient AR-to-diffusion conversion with minimal cost, preserving AR-level performance while enabling parallel generation.
  arXiv  Detail & Related papers  (2025-10-07T17:29:28Z)
• RAPID^3: Tri-Level Reinforced Acceleration Policies for Diffusion Transformer [86.57077884971478]
  Diffusion Transformers (DiTs) excel at visual generation yet remain hampered by slow sampling.<n>We introduce RAPID3: Tri-Level Reinforced Acceleration Policies for Diffusion Transformers.<n>It delivers image-wise acceleration with zero updates to the base generator.<n>It achieves nearly 3x faster sampling with competitive generation quality.
  arXiv  Detail & Related papers  (2025-09-26T13:20:52Z)
• FlashDLM: Accelerating Diffusion Language Model Inference via Efficient KV Caching and Guided Diffusion [22.207275433870937]
  Diffusion language models offer parallel token generation and inherent bidirectionality.<n>State-of-the-art diffusion models (e.g., Dream 7B, LLaDA 8B) suffer from slow inference.<n>We introduce Guided Diffusion, a training-free method that uses a lightweight pretrained autoregressive model to supervise token unmasking.
  arXiv  Detail & Related papers  (2025-05-27T17:39:39Z)

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.