Preprint2026
FVAttn: Adaptive Sparse Attention with Runtime Load Balancing for Video Generation
Hao Liu, Chenghuan Huang, Ye Huang, et al.
FVAttn is a training-free sparse-attention system that uses runtime load balancing and slack-aware augmentation to improve distributed execution efficiency for video generation.
0Jul 17, 2026TransformersAttention Mechanisms
arXiv