SPADE combines static, semi-static, and dynamic block-sparse attention with a cheap SICS-based blocking heuristic to speed up video diffusion inference by up to 1.80x end-to-end.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
SPADE: An Input-Adaptive Sparse Attention Engine for Fast Video Diffusion Models Inference
SPADE combines static, semi-static, and dynamic block-sparse attention with a cheap SICS-based blocking heuristic to speed up video diffusion inference by up to 1.80x end-to-end.