这篇论文提出了ChebBooster，一种基于切比雪夫多项式的训练免费外推框架，能显著提升扩散Transformer的推理效率，值得一看。
ChebBooster通过切比雪夫多项式理论实现训练免费的外推框架，为扩散Transformer（DiTs）提供稳定高效的加速。在DiT-XL/2、PixArt-$Σ$和FLUX.1-dev等三个代表性模型上，ChebBooster在视觉质量和推理效率上均取得显著提升，达到$3.68 imes$延迟速度提升和$5.12 imes$浮点运算减少，优于现有训练免费基线。
ChebBooster: A Training-Free Approach for Efficient Diffusion Transformer Inference via Chebyshev-Inspired Extrapolation
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.