SageAttention3: Microscaling FP4 Attention for Inference and An Exploration of 8-Bit Training

Jintao Zhang, Jia wei, Haoxu Wang, Pengle Zhang, Xiaoming Xu, Haofeng Huang, Kai Jiang, Jun Zhu, Jianfei Chen

Keywords: Attention, Quantization, Efficient Attention, GPU Kernel

TL;DR: SageAttention3: Microscaling FP4 Attention for Plug-and-Play Inference Acceleration and An Exploration of 8-Bit Attention for Training.

Abstract: The efficiency of attention is important due to its quadratic time complexity. We enhance the efficiency of attention through two key contributions: First, we leverage the new $\texttt{FP4}$ Tensor Cores in Blackwell GPUs to accelerate attention computation. Our implementation achieves $\textbf{1038}$ $\texttt{TOPS}$ on $\texttt{RTX5090}$, which is a $\textbf{5}\times$ speedup over the fastest FlashAttention on $\texttt{RTX5090}$. Experiments show that our $\texttt{FP4}$ attention can accelerate inference of various models in a plug-and-play way. Second, we pioneer low-bit attention to training tasks. Existing low-bit attention works like FlashAttention3 and SageAttention focus only on inference. However, the efficiency of training large models is also important. To explore whether low-bit attention can be effectively applied to training tasks, we design an accurate and efficient $\texttt{8-bit}$ attention for both forward and backward propagation. Experiments indicate that $\texttt{8-bit}$ attention achieves lossless performance in fine-tuning tasks but exhibits slower convergence in pretraining tasks. The code is available at https://github.com/thu-ml/SageAttention.

Primary Area: Infrastructure (e.g., libraries, improved implementation and scalability, distributed solutions)

Submission Number: 22679