aojunzz / NM-sparsity
☆212Updated last year
Related projects: ⓘ
- Pytorch implementation of BRECQ, ICLR 2021☆247Updated 3 years ago
- The official PyTorch implementation of the ICLR2022 paper, QDrop: Randomly Dropping Quantization for Extremely Low-bit Post-Training Quan…☆107Updated last year
- PyTorch implementation of Data Free Quantization Through Weight Equalization and Bias Correction.☆256Updated 11 months ago
- [ICLR 2022 Oral] F8Net: Fixed-Point 8-bit Only Multiplication for Network Quantization☆96Updated 2 years ago
- Unofficial implementation of LSQ-Net, a neural network quantization framework☆269Updated 4 months ago
- Post-Training Quantization for Vision transformers.☆176Updated 2 years ago
- Nonuniform-to-Uniform Quantization: Towards Accurate Quantization via Generalized Straight-Through Estimation. In CVPR 2022.☆112Updated 2 years ago
- ☆186Updated 2 years ago
- [CVPR'20] ZeroQ: A Novel Zero Shot Quantization Framework☆274Updated 9 months ago
- Code for the NeurIPS 2022 paper "Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning".☆95Updated last year
- This repository contains integer operators on GPUs for PyTorch.☆172Updated 11 months ago
- ☆67Updated 2 years ago
- ☆113Updated last year
- [IJCAI 2022] FQ-ViT: Post-Training Quantization for Fully Quantized Vision Transformer☆301Updated last year
- The PyTorch implementation of Learned Step size Quantization (LSQ) in ICLR2020 (unofficial)☆123Updated 3 years ago
- Quantization library for PyTorch. Support low-precision and mixed-precision quantization, with hardware implementation through TVM.☆410Updated last year
- Improving Post Training Neural Quantization: Layer-wise Calibration and Integer Programming☆94Updated 3 years ago
- PyTorch implementation for the APoT quantization (ICLR 2020)☆265Updated last year
- Code for our paper at ECCV 2020: Post-Training Piecewise Linear Quantization for Deep Neural Networks☆66Updated 2 years ago
- Quantization of Convolutional Neural networks.☆237Updated last month
- The official PyTorch implementation of the NeurIPS2022 (spotlight) paper, Outlier Suppression: Pushing the Limit of Low-bit Transformer L…☆46Updated last year
- Official implementation of the EMNLP23 paper: Outlier Suppression+: Accurate quantization of large language models by equivalent and opti…☆38Updated 10 months ago
- [ICML'21 Oral] I-BERT: Integer-only BERT Quantization