5 papers
QuantSR+: Pushing the Limit of Quantized Image Super-Resolution Networks
Haotong Qin, Xudong Ma, Xianglong Liu +4
Low-bit quantization is widely used to compress super-resolution (SR) models and reduce storage and computation costs for deployment on resource-limited devices. However, when SR m…
BWTA: Accurate and Efficient Binarized Transformer by Algorithm-Hardware Co-design
Yifu Ding, Xianglong Liu, Shenghao Jin +2
Ultra low-bit quantization brings substantial efficiency for Transformer-based models, but the accuracy degradation and limited GPU support hinder its wide usage. In this paper, we…
Diagonal-Tiled Mixed-Precision Attention for Efficient Low-Bit MXFP Inference
Yifu Ding, Xinhao Zhang, Jinyang Guo
Transformer-based large language models (LLMs) have demonstrated remarkable performance across a wide range of real-world tasks, but their inference cost remains prohibitively high…
APHQ-ViT: Post-Training Quantization with Average Perturbation Hessian Based Reconstruction for Vision Transformers
Zhuguanyu Wu, Jiayi Zhang, Jiaxin Chen +3
Vision Transformers (ViTs) have become one of the most commonly used backbones for vision tasks. Despite their remarkable performance, they often suffer significant accuracy drops…
TCAQ-DM: Timestep-Channel Adaptive Quantization for Diffusion Models
Haocheng Huang, Jiaxin Chen, Jinyang Guo +2
Diffusion models have achieved remarkable success in the image and video generation tasks. Nevertheless, they often require a large amount of memory and time overhead during infere…