Preprint
Sep 2026
WaveAlign: Cache-Aware Query-Row Scheduling for Sparse Attention in Long-Video Generation
Long-video generation with diffusion transformers (DiTs) produces extremely long token sequences, making attention a dominant inference bottleneck. Dynamic sparse attention reduces computation, but its realized speedup remains limited because irregular query-row execution degrades L2 cache locality and increases HBM tr...
Zi-Jian Dai, Sen-Khoo Han, You-Hui Bai et al.
· 0 citations