Jul 2026
HeadCast: Casting Attention Heads for Efficient Autoregressive Video Generation
HeadCast is proposed, a training-free, plug-and-play acceleration framework built on the observation that a pre-trained AR model's attention heads exhibit stable, heterogeneous behaviors that accelerates inference by up to 1.62x at 720P and 1.95x at 1080P, while keeping VBench quality on par with full attention and lar...
Jinliang Shen, Li Su, Zheming Li et al.
· arXiv.org · 1 citation