Sol-Attn：通过即时注意力稀疏化加速视频生成推理
Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification
浏览论文内容
中文总结 AI 辅助
研究针对扩散变压器视频生成中注意力推理瓶颈，提出无训练的Sol-Attn方法，通过即时块阈值处理和代理分数重用统一动态路由等，在图像和视频生成任务实验中实现质量-效率提升，加速视频生成和编辑。
中文摘要 AI 辅助
扩散变换器对于高保真视频生成至关重要，但长令牌序列使注意力成为主要推理瓶颈。无训练动态稀疏注意力通过仅计算选定的键值块来缓解此瓶颈，但现有方法在有效且准确地稀疏注意力方面存在困难。原因如下：（1）刚性、不可预测且成本高昂的路由；（2）有损的保留或丢弃稀疏化。本文介绍了无训练的Sol-Attn，它在单次在线softmax过程中统一了动态路由、稀疏计算和近似校正，在稀疏注意力方面实现了更好的精度-效率权衡。其核心是即时块阈值处理和代理分数重用。实验表明，Sol-Attn提升了无训练稀疏注意力的质量-效率前沿，在视频生成和编辑中分别实现了2.1倍和2.3倍的端到端加速，同时保持视觉质量。
英文摘要
Diffusion transformers are essential for high-fidelity video generation, but long token sequences make attention a dominant inference bottleneck. Training-free dynamic sparse attention alleviates this bottleneck by computing only selected key-value blocks, yet existing methods struggle to sparsify attention both efficiently and accurately for two reasons: (1) Rigid, unpredictable, and costly routing: selecting a fixed fraction of top-ranked blocks by proxy score imposes fixed budgets, whereas retaining blocks to reach a target cumulative proxy probability mass yields dynamic but potentially imbalanced budgets; both incur non-negligible overhead from computing and materializing proxy scores. (2) Lossy keep-or-drop sparsification: unselected blocks are discarded entirely, degrading accuracy under aggressive sparsity. These limitations motivate cheaper dynamic-budget routing while limiting accuracy degradation. In this paper, we introduce training-free Sol-Attn (Sparsifying online attention), which unifies dynamic routing, sparse computation, and approximation correction in a single online-softmax pass, achieving a better accuracy-efficiency trade-off in sparse attention. The core of Sol-Attn is on-the-fly block thresholding with proxy-score reuse, which selects critical blocks by comparing block proxy scores against a threshold during online softmax. This design enables dynamic yet controllable block budgets without materializing the proxy map, while directly reusing the proxy scores of unselected blocks to approximate their contribution. Experiments across image and video generation tasks show that Sol-Attn advances the quality-efficiency frontier of training-free sparse attention, delivering 2.1 times and 2.3 times end-to-end speedups for video generation and editing, respectively, while preserving visual quality.
