Research
Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification
arXiv:2607.24027v1 Announce Type: new Abstract: Diffusion transformers are essential for high-fidelity video generation, but long token sequences make attention a dominant inference bottleneck. Traini
arXiv:2607.24027v1 Announce Type: new Abstract: 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.
Related
- RoPeSLR: 3D RoPE-driven Sparse-LowRank Attention for Efficient Diffusion Transformers
- FG-Attn: Leveraging Fine-Grained Sparse Attention in Video Diffusion Models
- Attention Sparsity is Input-Stable: Training-Free Sparse Attention for Video Generation via Offline Sparsity Profiling and Online QK Co-Clustering
- Mixture of Distributions Matters: Dynamic Sparse Attention for Efficient Video Diffusion Transformers
Source: arXiv cs.CV | 2026-07-28