PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models
Paper
•
2506.16054
•
Published
•
60
•
2
Tianchen Zhao
A-suozhang
AI & ML interests
efficient deep learning
Recent Activity
authored
a paper
about 1 month ago
DiTFastAttn: Attention Compression for Diffusion Transformer Models
authored
a paper
about 1 month ago
PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and
Quantized Attention in Visual Generation Models
Organizations
commented
a
paper
about 1 month ago