用切比雪夫多项式实现无需训练的高效扩散模型推理加速
ChebBooster: A Training-Free Approach for Efficient Diffusion Transformer Inference via Chebyshev-Inspired Extrapolation
- 基于切比雪夫多项式理论，设计数值稳定且低开销的外推机制
- 在多个模型上实现最高3.68倍加速与5.12倍计算量减少
- 适合追求推理效率的高保真图像生成应用
扩散Transformer（DiTs）在高质量图像生成中表现优异，但其采样过程因每一步都需完整执行模型而计算成本高昂。尽管已有基于缓存的加速方法，但简单复用策略在长间隔下准确率下降，基于泰勒展开的外推方法常受龙格振荡影响而不稳定。本文提出ChebBooster，一种基于切比雪夫多项式理论的免训练外推框架，实现稳定高效的DiT推理加速。我们采用分段重心公式评估切比雪夫近似，具备高数值稳定性且开销极小，并将外推分解为离线权重预计算和轻量在线应用两个阶段。在DiT-XL/2、PixArt-Σ和FLUX.1-dev三类代表性模型上的大量实验表明，ChebBooster在多种生成任务与分辨率下均显著提升视觉质量与推理效率，最高达3.68倍延迟加速和5.12倍浮点运算量（FLOPs）减少，优于现有免训练基线方法。
原文摘要 · Abstract (English)
Diffusion Transformers (DiTs) have shown strong performance in high-fidelity image generation, but their sampling process remains computationally intensive due to full model execution at every timestep. While cache-based acceleration has been explored to mitigate inference cost, naive reuse schemes suffer from low accuracy over long intervals, and Taylor-series-based extrapolation methods often face instability caused by Runge oscillations. In this paper, we propose ChebBooster, a training-free extrapolation framework based on Chebyshev polynomial theory that achieves stable and efficient acceleration for DiTs. Specifically, we adopt the Barycentric formulation to evaluate Chebyshev approximants with high numerical stability and minimal overhead, and further decouple the extrapolation into an offline weight precomputation phase and a lightweight online application stage. Extensive experiments across three representative DiT-based models, including DiT-XL/2, PixArt-$Σ$, and FLUX.1-dev, demonstrate that ChebBooster achieves consistent improvements in visual quality and inference efficiency, reaching up to $3.68\times$ latency speedup and $5.12\times$ FLOPs reduction, outperforming existing training-free baselines under diverse generation tasks and resolutions.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。