ChebBooster：一种基于切比雪夫启发式外推的无训练高效扩散Transformer推理方法

中文摘要 AI 辅助

扩散Transformer（DiTs）在高保真图像生成中表现出优异性能，但由于每一时间步都需执行完整模型，其采样过程仍存在计算密集的问题。虽然已有研究探索基于缓存的加速方法以降低推理成本，但简单的复用方案在长间隔下准确率较低，而基于泰勒级数的外推方法常因龙格振荡出现不稳定性。本文提出ChebBooster，一种基于切比雪夫多项式理论的无训练外推框架，可实现DiTs的稳定高效加速。具体而言，采用重心公式评估切比雪夫近似式，兼具高数值稳定性与最小开销，并将外推过程解耦为离线权重预计算阶段与轻量在线应用阶段。在DiT-XL/2、PixArt-Σ、FLUX.1-dev三种代表性DiT模型上开展的大量实验表明，ChebBooster在视觉质量与推理效率上均实现持续提升，最高可达成3.68倍延迟加速、5.12倍浮点运算量（FLOPs）降低，在各类生成任务与分辨率下均优于现有无训练基线方法。

英文摘要

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.

发表机构

• College of Electronics and Information Engineering, Shenzhen University（深圳大学电子与信息工程学院）
• School of Artificial Intelligence, Shenzhen University（深圳大学人工智能学院）

机构由 AI 辅助整理，请以论文原文为准。