# db-SP: Accelerating Sparse Attention for Visual Generative Models with Dual-Balanced Sequence Parallelism

arXiv: https://arxiv.org/abs/2511.23113 · HTML: https://mlsanity.com/paper/2511.23113/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Video generation, one of 14 directions in Diffusion models.
- Builds on 25 of its 33 references that are in the map.
- First posted on arXiv 28 Nov 2025.

## Placed in

- Diffusion models / [Video generation](https://mlsanity.com/diffusion/video-generation/)

## Builds on (most cited first, 25 of 25)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [ViViT: A Video Vision Transformer](https://mlsanity.com/paper/2103.15691/) (2021)
- [Open-Sora: Democratizing Efficient Video Production for All](https://mlsanity.com/paper/2412.20404/) (2024)
- [Ring Attention with Blockwise Transformers for Near-Infinite Context](https://mlsanity.com/paper/2310.01889/) (2023)
- [Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity](https://mlsanity.com/paper/2502.01776/) (2025)
- [Open-Sora 2.0: Training a Commercial-Level Video Generation Model in 200k](https://mlsanity.com/paper/2503.09642/) (2025)
- [SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Acceleration](https://mlsanity.com/paper/2410.02367/) (2024)
- [Accelerating Diffusion Transformers with Token-wise Feature Caching](https://mlsanity.com/paper/2410.05317/) (2024)
- [FasterCache: Training-Free Video Diffusion Model Acceleration with High Quality](https://mlsanity.com/paper/2410.19355/) (2024)
- [DiTFastAttn: Attention Compression for Diffusion Transformer Models](https://mlsanity.com/paper/2406.08552/) (2024)
- [SageAttention2: Efficient Attention with Thorough Outlier Smoothing and Per-thread INT4 Quantization](https://mlsanity.com/paper/2411.10958/) (2024)
- [Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutation](https://mlsanity.com/paper/2505.18875/) (2025)
- [DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models](https://mlsanity.com/paper/2402.19481/) (2024)
- [Training-free and Adaptive Sparse Attention for Efficient Long Video Generation](https://mlsanity.com/paper/2502.21079/) (2025)
- [xDiT: an Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism](https://mlsanity.com/paper/2411.01738/) (2024)
- [PipeFusion: Patch-level Pipeline Parallelism for Diffusion Transformers Inference](https://mlsanity.com/paper/2405.14430/) (2024)
- [Sliding Window Attention Training for Efficient Large Language Models](https://mlsanity.com/paper/2502.18845/) (2025)
- [SmoothCache: A Universal Inference Acceleration Technique for Diffusion Transformers](https://mlsanity.com/paper/2411.10510/) (2024)
- [PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models](https://mlsanity.com/paper/2506.16054/) (2025)
- [BurstAttention: An Efficient Distributed Attention Framework for Extremely Long Sequences](https://mlsanity.com/paper/2403.09347/) (2024)
- [DiffServe: Efficiently Serving Text-to-Image Diffusion Models with Query-Aware Model Scaling](https://mlsanity.com/paper/2411.15381/) (2024)
- [BurstEngine: an Efficient Distributed Framework for Training Transformers on Extremely Long Sequences of over 1M Tokens](https://mlsanity.com/paper/2509.19836/) (2025)

## Built on by (most cited first, 3 of 3)

- [Efficient Video Diffusion Models: Advancements and Challenges](https://mlsanity.com/paper/2604.15911/) (2026)
- [FVAttn: Adaptive Sparse Attention with Runtime Load Balancing for Video Generation](https://mlsanity.com/paper/2607.16190/) (2026)
- [SparSP: Exploiting Communication Sparsity for Sequence-Parallel Video DiTs](https://mlsanity.com/paper/2609.32197/) (2026)

## Abstract (arXiv)

Scaling Diffusion Transformer (DiT) inference via sequence parallelism is critical for reducing latency in visual generation, but is severely hampered by workload imbalance when applied to models employing block-wise sparse attention. The imbalance stems from the inherent variation in sparsity across attention heads and the irregular distribution of dense blocks within the sparse mask, when sequence parallelism is applied along the head dimension (as in Ulysses) or the block dimension (as in Ring Attention). In this paper, we formalize a sparse imbalance ratio to quantify the imbalance, and propose db-SP, a sparsity-aware sequence parallelism technique that tackles the challenge. db-SP contains a dual-level partitioning approach that achieves near-perfect workload balance at both the head and block levels with negligible overhead. Furthermore, to handle the evolving sparsity patterns across denoising steps and layers, db-SP dynamically determines the parallel degrees for the head and block dimensions at runtime. Experimental results demonstrate that db-SP delivers an end-to-end speedup of 1.25x and an attention-specific speedup of 1.40x over state-of-the-art sequence parallel methods on average. Code is available at https://github.com/thu-nics/db-SP.