SageAttention2: Efficient Attention with Thorough Outlier Smoothing and Per-thread INT4 Quantization

Jintao Zhang, Haofeng Huang, Pengle Zhang, Jia wei, Jun Zhu, Jianfei Chen

TL;DR: Efficient Attention with Thorough Outlier Smoothing and Per-thread INT4 Quantization.

Abstract: Although quantization for linear layers has been widely used, its application to accelerate the attention process remains limited. To further enhance the efficiency of attention computation compared to SageAttention while maintaining precision, we propose SageAttention2, which utilizes significantly faster 4-bit matrix multiplication (Matmul) alongside additional precision-enhancing techniques. First, we propose to quantize matrixes $(Q, K)$ to INT4 in a hardware-friendly thread-level granularity and quantize matrixes $(\widetilde P, V)$ to FP8. Second, we propose a method to smooth $Q$, enhancing the accuracy of INT4 $QK^\top$. Third, we propose a two-level accumulation strategy for $\widetilde PV$ to enhance the accuracy of FP8 $\widetilde PV$. The operations per second (OPS) of SageAttention2 surpass FlashAttention2 and xformers by about **3x** and **4.5x**, respectively. Moreover, SageAttention2 matches the speed of FlashAttention3(fp8) on the Hopper GPUs, while delivering much higher accuracy. Comprehensive experiments confirm that our approach incurs negligible end-to-end metrics loss across diverse models, including those for language, image, and video generation.

Lay Summary: Although quantization for linear layers has been widely used, its application to accelerate the attention process remains limited. To further enhance the efficiency of attention computation compared to SageAttention while maintaining precision, we propose SageAttention2. The operations per second (OPS) of SageAttention2 surpass FlashAttention2 and xformers by about **3x** and **4.5x**, respectively. Moreover, SageAttention2 matches the speed of FlashAttention3(fp8) on the Hopper GPUs, while delivering much higher accuracy. Comprehensive experiments confirm that our approach incurs negligible end-to-end metrics loss across diverse models, including those for language, image, and video generation.

Link To Code: https://github.com/thu-ml/SageAttention

Primary Area: Deep Learning->Attention Mechanisms

Keywords: Efficient attention, quantization, inference acceleration, Dit, video generation, AI Infrastructure, LLM Infrastructure

Submission Number: 3008