SODA：面向敏感性的扩散 Transformer 动态加速
SODA: Sensitivity-Oriented Dynamic Acceleration for Diffusion Transformer
对做扩散 Transformer 采样加速的人，这篇给出了一个可复用的思路：用离线敏感性误差建模（跨时间步、层、模块）作为代价函数，用动态规划求最优缓存间隔，并在剪枝与缓存复用时按 token 敏感性自适应决定剪枝时机与比例，可直接嵌入现有 DiT 推理管线以在可控加速比下提升保真度。
原文依据 The cache intervals are optimized via dynamic programming with sensitivity error as the cost function
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论扩散 Transformer 已成为视觉生成的主流范式，但其低推理效率仍是阻碍进一步发展的关键瓶颈。在常见的免训练技术中，缓存具有很高的加速效率，但往往损害保真度；而剪枝则表现出相反的权衡。将缓存与剪枝结合可在加速与生成质量之间取得平衡。然而，现有方法通常采用固定且启发式的方案来配置缓存与剪枝策略。尽管它们大致遵循生成模型对加速的整体敏感性趋势，却无法捕捉细粒度且复杂的变化，不可避免地跳过高度敏感的计算，从而导致质量下降。此外，这类人工设计的策略泛化性较差。为解决这些问题，我们提出 SODA，一种面向敏感性的动态加速方法，基于细粒度敏感性自适应地执行缓存与剪枝。SODA 构建了一个跨时间步、层和模块的离线敏感性误差建模框架，以捕捉对不同加速操作的敏感性。缓存间隔通过以敏感性误差为代价函数的动态规划进行优化，从而最小化缓存对模型敏感性的影响。在剪枝与缓存复用过程中，SODA 自适应地确定剪枝时机与比例，以保留高度敏感 token 的计算，显著提升生成保真度。在 DiT-XL/2、PixArt-\alpha 和 OpenSora 上的大量实验表明，SODA 在可控加速比下达到了最优的生成保真度。我们的代码已公开于：https://github.com/leaves162/SODA。
英文原文摘要 1774 字符
Diffusion Transformers have become a dominant paradigm in visual generation, yet their low inference efficiency remains a key bottleneck hindering further advancement. Among common training-free techniques, caching offers high acceleration efficiency but often compromises fidelity, whereas pruning shows the opposite trade-off. Integrating caching with pruning achieves a balance between acceleration and generation quality. However, existing methods typically employ fixed and heuristic schemes to configure caching and pruning strategies. While they roughly follow the overall sensitivity trend of generation models to acceleration, they fail to capture fine-grained and complex variations, inevitably skipping highly sensitive computations and leading to quality degradation. Furthermore, such manually designed strategies exhibit poor generalization. To address these issues, we propose SODA, a Sensitivity-Oriented Dynamic Acceleration method that adaptively performs caching and pruning based on fine-grained sensitivity. SODA builds an offline sensitivity error modeling framework across timesteps, layers, and modules to capture the sensitivity to different acceleration operations. The cache intervals are optimized via dynamic programming with sensitivity error as the cost function, minimizing the impact of caching on model sensitivity. During pruning and cache reuse, SODA adaptively determines the pruning timing and rate to preserve computations of highly sensitive tokens, significantly enhancing generation fidelity. Extensive experiments on DiT-XL/2, PixArt-\alpha, and OpenSora demonstrate that SODA achieves state-of-the-art generation fidelity under controllable acceleration ratios. Our code is released publicly at: https://github.com/leaves162/SODA.