Paper page - AB-Attention: Accurate Block Attention for Accelerating Video Diffusion Transformers

Source: https://huggingface.co/papers/2610.39663 Published on Oct 29

·

Submitted byhttps://huggingface.co/xubinknight

Xubinon Oct 30

Abstract

AB-Attention approximates dense video diffusion attention with high sparsity via intra-block clustering, weighted sampling, and fine-grained kernel gathering, improving fidelity and speed.

Video diffusion transformersgenerate high-quality videos, but the quadratic cost of3D full attentiondominates their inference.Dynamic block-sparse attentionreduces this cost by computing exact attention only on key/value blocks selected from current activations. However, its fidelity degrades under aggressive sparsity: blocks are scored from coarse summaries or formed by costly global clustering, pruned blocks vanish from the softmax, and whole tiles are kept or dropped even when only a few of their keys matter. To address these limitations, we propose Accurate Block Attention (AB-Attention), a training-free method that accurately approximates dense attention at high sparsity. ItsIntra-Block Clustering Selector(IBCS) estimates block importance faithfully yet cheaply by clustering queries only within each query block, without permuting tokens. Sampling withInclusion-Probability Weighting(SIP) then samples blocks in proportion to these estimates and reweights them by inverse inclusion probability, so that one pass estimates dense attention rather than truncating it. Finally, its kernel gathers key/value blocks much smaller than a tile into fulltensor-core tiles, refining selection at no extra tensor-core cost. On Wan2.1 and HunyuanVideo,AB-Attentionskips 89--92\% of attention, whereas the baselines compute 1.8--3.6times as much, yet it still improves PSNR by up to 4.4~dB over the strongest baseline and achieves up to 2.23times end-to-end speedup. Our code is available at https://github.com/InfRec-Cardinal/AB-Attention.

View arXiv pageView PDFProject pageGitHub23Add to collection

Get this paper in your agent:

hf papers read 2610\.39663

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2610.39663 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2610.39663 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2610.39663 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.