SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillation Paper • 2503.09641 • Published Mar 12 • 40
PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models Paper • 2506.16054 • Published Jun 19 • 60
SageAttention3: Microscaling FP4 Attention for Inference and An Exploration of 8-Bit Training Paper • 2505.11594 • Published May 16 • 75