跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.24479 · v1

Every Query Routes Itself: Accelerating Video Diffusion Transformers with Per-Query Routed Sparse Attention

首次提交 2026-11-18 22:17
版本更新 2026-11-18 22:17
雷达观测 2026-11-19 15:04
arXiv ↗PDF ↗

摘要

Self-attention over long token sequences dominates the inference cost of video diffusion transformers. Clustering-based sparse attention clusters both queries and keys and lets all queries in a cluster share one selection of key clusters. We show that this sharing limits accuracy: with key clusters and density fixed, attention grows more accurate as the query clusters are refined, and is most accurate when each query selects on its own, which needs no query clustering at all. We therefore propose Per-Query Routed Sparse Attention (PQRS), a training-free method that clusters only keys, lets each query select its own key clusters, and compensates for the unselected ones with their centroids. Per-query selections leave no query tile with a shared key list, so PQRS traverses key clusters instead of queries, buckets queries with identical selections into dense tasks, and merges their partial results in one pass under a fixed softmax offset carried from the previous denoising step. On four text-to-video and image-to-video models from the Wan and HunyuanVideo families, PQRS is the fastest of all the sparse attention methods we evaluate and the closest to the dense output, reaching 28.928.9 dB PSNR on Wan2.1-T2V and 35.435.4 dB on HunyuanVideo at 1.661.66--2.10×2.10\times end-to-end speedup.

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v1 · 2026-11-18 22:17 · 最新观测版本

Every Query Routes Itself: Accelerating Video Diffusion Transformers with Per-Query Routed Sparse Attention

Self-attention over long token sequences dominates the inference cost of video diffusion transformers. Clustering-based sparse attention clusters both queries and keys and lets all queries in a cluster share one selection of key clusters. We show that this sharing limits accuracy: with key clusters and density fixed, attention grows more accurate as the query clusters are refined, and is most accurate when each query selects on its own, which needs no query clustering at all. We therefore propose Per-Query Routed Sparse Attention (PQRS), a training-free method that clusters only keys, lets each query select its own key clusters, and compensates for the unselected ones with their centroids. Per-query selections leave no query tile with a shared key list, so PQRS traverses key clusters instead of queries, buckets queries with identical selections into dense tasks, and merges their partial results in one pass under a fixed softmax offset carried from the previous denoising step. On four text-to-video and image-to-video models from the Wan and HunyuanVideo families, PQRS is the fastest of all the sparse attention methods we evaluate and the closest to the dense output, reaching 28.928.9 dB PSNR on Wan2.1-T2V and 35.435.4 dB on HunyuanVideo at 1.661.66--2.10×2.10\times end-to-end speedup.

查看此版本解读 →查看此版本原文 ↗