HGA-Quant: Heterogeneity-Aware Quantization for AutoRegressive Visual Generation Models
A training-free PTQ framework for ARVG, consisting of Tail-Aware Bounded-init Grid Refinement (T-BGR) and Coarse-to-Fine Activation Precision Scheduling (CAPS), which achieves near full-precision image generation quality at an effective W4A5.6 activation precision.
Xin-Meng Liu, Xiang-Long Yan, Kai-Cheng Yang et al.
· 0 citations