Megadose AI progress, ranked and analyzed.

FVAttn: Adaptive Sparse Attention with Runtime Load Balancing for Video Generation

· HF Daily Papers ·
FVAttn targets the straggler problem created when adaptive sparse attention leaves some GPU ranks with heavier work than others.

The paper describes a training-free sparse-attention system for Video Diffusion Transformers. It combines Top-p routing, a Top-k safety floor, and video-aware block organization, then adjusts the attention mask at runtime. Its load balancer migrates a small number of heavy heads over P2P links, while unused rank slack is filled with extra high-value blocks. On step-distilled Wan2.2 I2V, the authors report load imbalance falling from 1.34 to 1.08, with a 4.41x attention speedup over FlashAttention and 2.02-2.11x DiT inference speedup. HF Daily Papers' note

score 4

Categories: Research