PAROAttention permutes tokens along frame, height, and width axes to make visual attention block-wise, enabling sparse and INT8/INT4 quantized attention with near-baseline generation quality.
Hardware acceleration of sparse and irregular tensor computations of ml models: A survey and insights
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
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models
PAROAttention permutes tokens along frame, height, and width axes to make visual attention block-wise, enabling sparse and INT8/INT4 quantized attention with near-baseline generation quality.