4 papers · 1 filter
Shift-and-Sum Quantization for Visual Autoregressive Models
Jaehyeon Moon, Bumsub Ham
Post-training quantization (PTQ) enables efficient deployment of deep networks using a small set of data. Its application to visual autoregressive models (VAR), however, remains re…
AccuQuant: Simulating Multiple Denoising Steps for Quantizing Diffusion Models
Seunghoon Lee, Jeongwoo Choi, Byunggwan Son +3
We present in this paper a novel post-training quantization (PTQ) method, dubbed AccuQuant, for diffusion models. We show analytically and empirically that quantization errors for…
Toward INT4 Fixed-Point Training via Exploring Quantization Error for Gradients
Dohyung Kim, Junghyup Lee, Jeimin Jeon +2
Network quantization generally converts full-precision weights and/or activations into low-bit fixed-point values in order to accelerate an inference process. Recent approaches to…
Instance-Aware Group Quantization for Vision Transformers
Jaehyeon Moon, Dohyung Kim, Junyong Cheon +1
Post-training quantization (PTQ) is an efficient model compression technique that quantizes a pretrained full-precision model using only a small calibration set of unlabeled sample…