SageAttention3: Microscaling FP4 Attention for Inference and An Exploration of 8-Bit Training Paper • 2505.11594 • Published 8 days ago • 56
SageAttention2 Technical Report: Accurate 4 Bit Attention for Plug-and-play Inference Acceleration Paper • 2411.10958 • Published Nov 17, 2024 • 56