SageAttention3: Microscaling FP4 Attention for Inference and An Exploration of 8-Bit Training Paper • 2505.11594 • Published May 16, 2025 • 77
SageAttention2++: A More Efficient Implementation of SageAttention2 Paper • 2505.21136 • Published May 27, 2025 • 45
SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Acceleration Paper • 2410.02367 • Published Oct 3, 2024 • 50
