Improving Video Sparse Attention with Fine-grained Router and Sparse Rebasing

Peiyuan Zhang; Guoqiang Wei; Yilong Zhao; Zixiang Zhang; Wei Zhou; Will Lin; Heng Zhang; Xiaonan Nie

cs.CVSep 26, 2026

Improving Video Sparse Attention with Fine-grained Router and Sparse Rebasing

Authors: Peiyuan Zhang, Guoqiang Wei, Yilong Zhao, Zixiang Zhang, Wei Zhou, Will Lin, Heng Zhang, Xiaonan Nie,

Organizations: University of California, San Diego · Work done during an internship at ByteDance Seed · ByteDance Seed · University of California, Berkeley ·

Abstract

We present VSA2, a frontier trainable sparse attention for video DiTs. VSA2 includes a variety of new architectural features and training procedures that we apply across all stages of the DiT development cycle, including pretraining, RL, and inference, to produce a DiT with comparable or better quality than a full attention counterpart. Architecturally, VSA2 introduces a fine-grained router that improves the precision of identifying critical tokens and supports dynamic computation by allowing each query to attend to a variable number of key-value pairs. In training, we identify a Hard-to-Easy Curriculum, where models trained under high sparsity and later evaluated with lower sparsity during inference not only generalize effectively, but also outperform models trained with full attention in motion quality. VSA2 is also flexible: it can replace full attention during the middle of progressive low-to-high resolution pretraining, rebasing early-stage full-attention checkpoints. Experiments show that VSA2 reduces attention computation by half over VSA with lower loss. On 720p videos, it accelerates attention by 8.9x and end-to-end generation by 4.62x compared to the FlashAttention-3 baseline, while achieving comparable or better video quality.

Figures & tables

Exp	Stage	Configuration				T2V			I2V
Exp	Stage	Train TopK	Infer TopK	Attn Sparsity	E2E Speedup	Motion	Following	Aesthetics	Motion	Following
1	480p	64	64	0.90	2.09 $\times$	-1.34%	1.34%	-0.67%	8.72%	1.34%
2	480p	64	128	0.82	1.92 $\times$	22.1%	-3.36%	-4.7%	6.71%	-8.72%
3	480p	32	128	0.82	1.92 $\times$	7.38%	-15.4%	-4.7%	11.4%	-9.4%
4	480p	32	64	0.90	2.09 $\times$	12.1%	-10.1%	-7.38%	4.03%	-4.03%
5	480p RL	64	64	0.90	2.09 $\times$	-4.03%	1.34%	-2.01%	8.05%	-4.7%

Table 2: Human evaluation results of VSA2 against full attention across various stages of video DiT training. A positive score means the model trained with VSA2 has better quality than its full attention counterpart at that stage.

Figure 4: Training loss and reward scores of VSA2 vs. full attention across various stages of video DiT training. With a sparsity ratio of 90% to 95%, VSA2 shows lower loss and similar reward scores compared to full attention.

Figure 7: Ablation studies of various design choices in video sparse attention. All models are trained from scratch except those in plot (f), which are initialized from a 256p video checkpoint.

Figure 8: Speed comparison on a single H800 GPU with batch size 1, number of heads 20, head dimension 128, and top64.

Appendix figures & tables3 assets

Supplementary material from the paper’s appendix.

Appendix

Figure 9: More text-to-video samples of VSA2 vs. full attention.

Figure 10: More image-to-video samples of VSA2 vs. full attention.

Figure 11: Trained on 5–12 s videos, VSA2 can directly generate 30 s videos.

Sparse Attention

Sparse attention reduces the token interactions computed by Transformers to lower the cost of long-context modeling and inference.

See all 245 papers

Parameterized Stripe Attention for Efficient Video Generation
Sep 29, 2026Xingyu Jia, Baole Ai, Ang Wang +2Video Diffusion Models Diffusion Transformer
Alibaba Group
SPADE: An Input-Adaptive Sparse Attention Engine for Fast Video Diffusion Models Inference
Aug 4, 2026Shanghao Liu, Renze Chen, Size Zheng +4Video Diffusion Models Diffusion Transformer
Eric · Beihang University · Peking University
Sparse Attention for Video Generation Acceleration via Growing Sparsity and Reduced Search
Oct 15, 2026Yun Dai, Yuyun Chen, Jiarui Wen +3Sparse Attention Diffusion Model Inference Acceleration
South China University of Technology

Sep 29, 2026J/K move · Enter open · S save

Parameterized Stripe Attention for Efficient Video Generation

Xingyu Jia, Baole Ai, Ang Wang, Kang Zhao+1

Alibaba Group

Video Diffusion Models Diffusion Transformer Sparse Attention Diffusion Model Inference Acceleration

Open paper AskPDF arXiv

Diffusion Transformers (DiTs) enable high-quality video generation but suffer from substantial inference latency, primarily attributable to the computationally expensive full spatio-temporal attention. While sparse attention methods offer potential solutions, existing approaches face an inherent flexibility--efficiency dilemma: predefined masks lack the flexibility to capture diverse attention patterns, while runtime-determined masks introduce overheads and sacrifice hardware efficiency. We identify the lack of a unified structural characterization of DiT attention as a key limitation of existing methods, and establish that video DiT attention exhibits periodic diagonal stripe structures along both temporal and spatial dimensions. To formally encode these structured patterns within a single efficient kernel, we present {\bf PSA}, a parameterized stripe attention that formalizes the observed stripe regularity, unifying diverse attention patterns for efficient mask generation. This unified representation enables a single hardware-efficient CUDA kernel to process all sparse patterns, achieving FlashAttention-3-level Model FLOPs Utilization. To determine optimal sparsity configurations, we propose a training-free offline search algorithm that automatically maximizes sparsity under a specified error tolerance for each attention head. Experiments on HunyuanVideo and Wan~2.1 demonstrate that PSA achieves 1.57

\times

and 1.37

\times

end-to-end speedups over FlashAttention-3 baselines, with acceptable visual quality degradation.

Abstract

Sparse Attention

Explore similar work

Parameterized Stripe Attention for Efficient Video Generation

SPADE: An Input-Adaptive Sparse Attention Engine for Fast Video Diffusion Models Inference

Sparse Attention for Video Generation Acceleration via Growing Sparsity and Reduced Search