Deflating the Hessian: Rank-4 W4A4 Quantization for Multimodal Diffusion Transformers
HSVDQuant is presented, a unified framework modeling low-rank-assisted W4A4 PTQ as a coupled calibration problem and deriving optimization-based solvers from the joint objective, which achieves better W4A4 performance with substantially lower rank and quantization cost.
Shi-Wen Wang, Peng-Xiang Zhao, Xiao-Ming Yuan
· 0 citations