# ClusterAttention: A training-free speedup of bidirectional attention

arXiv: https://arxiv.org/abs/2608.26965 · HTML: https://mlsanity.com/paper/2608.26965/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 37 of its 46 references that are in the map.
- First posted on arXiv 27 Aug 2026.

## Builds on (most cited first, 30 of 37)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [Rethinking Attention with Performers](https://mlsanity.com/paper/2009.14794/) (2020)
- [Linformer: Self-Attention with Linear Complexity](https://mlsanity.com/paper/2006.04768/) (2020)
- [DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence](https://mlsanity.com/paper/2606.19348/) (2026)
- [DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models](https://mlsanity.com/paper/2512.02556/) (2025)
- [FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision](https://mlsanity.com/paper/2407.08608/) (2024)
- [Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference](https://mlsanity.com/paper/2406.10774/) (2024)
- [Nystr"omformer: A Nystr"om-Based Algorithm for Approximating Self-Attention](https://mlsanity.com/paper/2102.03902/) (2021)
- [MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention](https://mlsanity.com/paper/2407.02490/) (2024)
- [MoBA: Mixture of Block Attention for Long-Context LLMs](https://mlsanity.com/paper/2502.13189/) (2025)
- [SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Acceleration](https://mlsanity.com/paper/2410.02367/) (2024)
- [TabICLv2: A better, faster, scalable, and open tabular foundation model](https://mlsanity.com/paper/2602.11139/) (2026)
- [On the Properties of the Softmax Function with Application in Game Theory and Reinforcement Learning](https://mlsanity.com/paper/1704.00805/) (2017)
- [XAttention: Block Sparse Attention with Antidiagonal Scoring](https://mlsanity.com/paper/2503.16428/) (2025)
- [Scatterbrain: Unifying Sparse and Low-rank Attention Approximation](https://mlsanity.com/paper/2110.15343/) (2021)
- [Fast Transformers with Clustered Attention](https://mlsanity.com/paper/2007.04825/) (2020)
- [SpargeAttention: Accurate and Training-free Sparse Attention Accelerating Any Model Inference](https://mlsanity.com/paper/2502.18137/) (2025)
- [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)
- [VSA: Faster Video Diffusion with Trainable Sparse Attention](https://mlsanity.com/paper/2505.13389/) (2025)
- [HyperAttention: Long-context Attention in Near-Linear Time](https://mlsanity.com/paper/2310.05869/) (2023)
- [SageAttention3: Microscaling FP4 Attention for Inference and An Exploration of 8-Bit Training](https://mlsanity.com/paper/2505.11594/) (2025)
- [FlashAttention-4: Algorithm and Kernel Pipelining Co-Design for Asymmetric Hardware Scaling](https://mlsanity.com/paper/2603.05451/) (2026)
- [TALENT: A Tabular Analytics and Learning Toolbox](https://mlsanity.com/paper/2407.04057/) (2024)
- [Bidirectional Sparse Attention for Faster Video Diffusion Training](https://mlsanity.com/paper/2509.01085/) (2025)
- [UltraGen: High-Resolution Video Generation with Hierarchical Attention](https://mlsanity.com/paper/2510.18775/) (2025)

## Abstract (arXiv)

We introduce ClusterAttention, a general training-free speedup of bidirectional attention at large token counts. We point out two common assumptions in contemporary training-free methods; attention sparsity, and context that can be leveraged, such as structure in the input or multiple similar forward passes, and show when they fail. Our proposed method utilizes a fast attention-aware recursive clustering method, and compensation of excluded clusters through their mean. The clustering method gives power-of-two cluster sizes, allowing block-sparse attention to match dense attention in GPU throughput. On TabPFN-3 arXiv:2605.13986, a model where none of the assumptions hold, ClusterAttention is to our knowledge the first method to provide a substantial speedup over the default attention, while consistently keeping over 99% of its accuracy. On the largest dataset from the TALENT benchmark suite, it makes processing of the training dataset close to 8x faster at nearly 11x attention speedup. ClusterAttention is also competitive with domain-specific methods, while avoiding any of the domain-specific engineering. On video-generation with Wan 2.1-T2V-14B arXiv:2503.20314 it produces output closer to dense attention at a larger speedup (1.8x vs 1.4x) than SVOO arXiv:2603.18636, a leading method in this domain, with both evaluated without offline calibration.