AdaSPEC: Selective Knowledge Distillation for Efficient Speculative Decoders Paper • 2510.19779 • Published Oct 22, 2025 • 60
SageAttention2++: A More Efficient Implementation of SageAttention2 Paper • 2505.21136 • Published May 27, 2025 • 45
SageAttention3: Microscaling FP4 Attention for Inference and An Exploration of 8-Bit Training Paper • 2505.11594 • Published May 16, 2025 • 75