collaborators

6 papers

cs.LG2026

TetraJet-v2: Accurate NVFP4 Training for Large Language Models with Oscillation Suppression and Outlier Control

Yuxiang Chen, Yifan Liu, Xiaoming Xu +5

Large Language Models (LLMs) training is prohibitively expensive, driving interest in low-precision fully-quantized training (FQT). While novel 4-bit formats like NVFP4 offer subst…

cs.LG2026

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

Jintao Zhang, Jia Wei, Pengle Zhang +6

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 FP4…

cs.LG2025

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

Jintao Zhang, Haofeng Huang, Pengle Zhang +3

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 co…

cs.LG2025

SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Acceleration

Jintao Zhang, Jia Wei, Haofeng Huang +3

The transformer architecture predominates across various models. As the heart of the transformer, attention has a computational complexity of , compared to for linea…

cs.LG2025

Accurate INT8 Training Through Dynamic Block-Level Fallback

Pengle Zhang, Jia Wei, Jintao Zhang +2

Transformer models have achieved remarkable success across various AI applications but face significant training costs. Low-bit training, such as INT8 training, can leverage comput…

cs.LG2025

SageAttention2++: A More Efficient Implementation of SageAttention2

Jintao Zhang, Xiaoming Xu, Jia Wei +5

The efficiency of attention is critical because its time complexity grows quadratically with sequence length. SageAttention2 addresses this by utilizing quantization to accelerate…