An open API service indexing awesome lists of open source software.

Awesome-Model-Quantization

A list of papers, docs, codes about model quantization. This repo is aimed to provide the info for model quantization research, we are continuously improving the project. Welcome to PR the works (papers, repositories) that are missed by the repo.
https://github.com/AI-Efficiency/Awesome-Model-Quantization

Last synced: about 4 hours ago
JSON representation

  • Benchmarks

    • [Paper
    • [Paper - Quantization)] [![GitHub stars](https://img.shields.io/github/stars/Macaronlin/LLaMA3-Quantization?style=social)](https://github.com/Macaronlin/LLaMA3-Quantization)
    • [Paper - ML/Qwen3-Quantization)] [![GitHub stars](https://img.shields.io/github/stars/Efficient-ML/Qwen3-Quantization?style=social)](https://github.com/Efficient-ML/Qwen3-Quantization)
    • [Paper
    • [Paper
  • Books

  • Papers

    • 2015

    • 2016

      • [CVPR - wu/quantized-cnn)
      • [arXiv - Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients [[code](https://github.com/tensorpack/tensorpack/tree/master/examples/DoReFa-Net)] [![GitHub stars](https://img.shields.io/github/stars/tensorpack/tensorpack?style=social)](https://github.com/tensorpack/tensorpack)
      • [ECCV - Net: ImageNet Classification Using Binary Convolutional Neural Networks [[code](https://github.com/allenai/XNOR-Net)] [![GitHub stars](https://img.shields.io/github/stars/allenai/XNOR-Net?style=social)](https://github.com/allenai/XNOR-Net)
      • [ICASSP - point Performance Analysis of Recurrent Neural Networks
      • [NeurIPS - 1 [[code](https://github.com/itayhubara/BinaryNet)] [![GitHub stars](https://img.shields.io/github/stars/itayhubara/BinaryNet?style=social)](https://github.com/itayhubara/BinaryNet)
      • [NeurIPS - chris/caffe-twns)] [![GitHub stars](https://img.shields.io/github/stars/fengfu-chris/caffe-twns?style=social)](https://github.com/fengfu-chris/caffe-twns)
    • 2017

      • [CVPR - wave Gaussian Quantization [[code](https://github.com/zhaoweicai/hwgq)] [![GitHub stars](https://img.shields.io/github/stars/zhaoweicai/hwgq?style=social)](https://github.com/zhaoweicai/hwgq)
      • [CVPR
      • [arXiv - Source Binary Neural Network Implementation Based on MXNet [[code](https://github.com/hpi-xnor)]
      • [FPGA
      • [ICASSP - point optimization of deep neural networks with adaptive step size retraining
      • [ICCV - cnn-landmarks)]
      • [ICCV - Order Residual Quantization
      • [ICLR - Precision Weights [[code](https://github.com/Mxbonn/INQ-pytorch)] [![GitHub stars](https://img.shields.io/github/stars/Mxbonn/INQ-pytorch?style=social)](https://github.com/Mxbonn/INQ-pytorch)
      • [ICLR - aware Binarization of Deep Networks [[code](https://github.com/houlu369/Loss-aware-Binarization)] [![GitHub stars](https://img.shields.io/github/stars/houlu369/Loss-aware-Binarization?style=social)](https://github.com/houlu369/Loss-aware-Binarization)
      • [ICLR - Sharing for Neural Network Compression
      • [ICLR - ternary-quantization)] [![GitHub stars](https://img.shields.io/github/stars/TropComplique/trained-ternary-quantization?style=social)](https://github.com/TropComplique/trained-ternary-quantization)
      • [IPDPSW - Chip Memory Based Binarized Convolutional Deep Neural Network Applying Batch Normalization Free Technique on an FPGA
      • [InterSpeech
      • [JETC - Outperforming FPGA Accelerator Architecture for Binary Convolutional Neural Networks
      • [MWSCAS
      • [NeurIPS - Binary-Convolution-Network)] [![GitHub stars](https://img.shields.io/github/stars/layog/Accurate-Binary-Convolution-Network?style=social)](https://github.com/layog/Accurate-Binary-Convolution-Network)
      • [Neurocomputing - BNN: Binarized neural network on FPGA
      • [arXiv - Precision Architecture for Inference of Convolutional Neural Networks [[code](https://github.com/gudovskiy/ShiftCNN)] [![GitHub stars](https://img.shields.io/github/stars/gudovskiy/ShiftCNN?style=social)](https://github.com/gudovskiy/ShiftCNN)
      • [arXiv - Grained Quantization
    • 2018

      • [AAAI
      • [AAAI
      • [CAAI
      • [CVPR - bitwidth Weights and Activations
      • [CVPR - error-aware quantization for low-bit deep neural networks
      • [CVPR
      • [CVPR - Arithmetic-Only Inference
      • [CVPR
      • [CVPR - bitwidth Convolutional Neural Networks
      • [CVPR - Step Quantization for Low-bit Neural Networks
      • [arXiv
      • [arXiv
      • [ECCV - Real Net: Enhancing the Performance of 1-bit CNNs With Improved Representational Capability and Advanced Training Algorithm [[code](https://github.com/liuzechun/Bi-Real-net)] [![GitHub stars](https://img.shields.io/github/stars/liuzechun/Bi-Real-net?style=social)](https://github.com/liuzechun/Bi-Real-net)
      • [ECCV - Nets: Learned Quantization for Highly Accurate and Compact Deep Neural Networks [[code](https://github.com/microsoft/LQ-Nets)] [![GitHub stars](https://img.shields.io/github/stars/microsoft/LQ-Nets?style=social)](https://github.com/microsoft/LQ-Nets)
      • [ECCV
      • [ECCV
      • [ECCV - Binary Decomposition
      • [FCCM
      • [FPL
      • [ICLR
      • [ICLR - Precision Network Accuracy
      • [ICLR - aware Weight Quantization of Deep Networks [[code](https://github.com/houlu369/Loss-aware-weight-quantization)] [![GitHub stars](https://img.shields.io/github/stars/houlu369/Loss-aware-weight-quantization?style=social)](https://github.com/houlu369/Loss-aware-weight-quantization)
      • [ICLR
      • [ICLR - Precision Networks
      • [IEEE J. Solid-State Circuits - Chip Binary/Ternary Reconfigurable in-Memory Deep Neural Network Accelerator Achieving 1.4 TOPS at 0.6 W
      • [IJCAI
      • [IJCAI
      • [IJCNN
      • [IPDPS
      • [MM - Time Low-Power Inference of Binary Neural Networks on CPUs
      • [NCA - based accelerators for convolutional neural networks
      • [NeurIPS - bit training of neural networks [[code](https://github.com/eladhoffer/quantized.pytorch)] [![GitHub stars](https://img.shields.io/github/stars/eladhoffer/quantized.pytorch?style=social)](https://github.com/eladhoffer/quantized.pytorch)
      • [NeurIPS - bit Floating Point Numbers
      • [Res Math Sci
      • [TCAD - fJ/op Binary Neural Network Inference
      • [TRETS - R: An End-to-End Deep-Learning Framework for Fast Exploration of Quantized Neural Networks
      • [TVLSI - Efficient Architecture for Binary Weight Convolutional Neural Networks
      • [arXiv - quantization)] [![GitHub stars](https://img.shields.io/github/stars/yukang2017/NAS-quantization?style=social)](https://github.com/yukang2017/NAS-quantization)
      • [arXiv - xnor/BMXNet-v2)] [![GitHub stars](https://img.shields.io/github/stars/hpi-xnor/BMXNet-v2?style=social)](https://github.com/hpi-xnor/BMXNet-v2)
    • 2019

      • [AAAI
      • [AAAI - bit CNNs via Discrete Back Propagation
      • [APCCAS
      • [BMVC
      • [BMVC - Net++: Improved Binary Neural Networks
      • [CVPR
      • [CVPR
      • [CVPR - bit DCNNs with Circulant Back Propagation
      • [CVPR
      • [CVPR - Aware Automated Quantization with Mixed Precision [[code](https://github.com/mit-han-lab/haq)] [![GitHub stars](https://img.shields.io/github/stars/mit-han-lab/haq?style=social)](https://github.com/mit-han-lab/haq)
      • [CVPR - Wise Interactions for Binary Convolutional Neural Networks
      • [CVPR
      • [CVPR - quantization-networks)] [![GitHub stars](https://img.shields.io/github/stars/aliyun/alibabacloud-quantization-networks?style=social)](https://github.com/aliyun/alibabacloud-quantization-networks)
      • [CVPR
      • [CVPR - Map Sparsity Through Low-Bit Quantization
      • [CVPR
      • [arXiv - xnor/BMXNet-v2)] [![GitHub stars](https://img.shields.io/github/stars/hpi-xnor/BMXNet-v2?style=social)](https://github.com/hpi-xnor/BMXNet-v2)
      • [arXiv
      • [arXiv
      • [arXiv
      • [arXiv - bit DCNNs
      • [arXiv - Ensemble Template for Accurate Binary Convolutional Neural Networks
      • [FPGA - Efficient Binarized Neural Network Inference on FPGA
      • [GLSVLSI
      • [ICCV - bit cnns
      • [ICCV - Free Quantization Through Weight Equalization and Bias Correction [[code](https://github.com/jakc4103/DFQ)] [![GitHub stars](https://img.shields.io/github/stars/jakc4103/DFQ?style=social)](https://github.com/jakc4103/DFQ)
      • [ICCV - Precision and Low-Bit Neural Networks
      • [ICCV
      • [ICCV - Precision
      • [ICCV
      • [ICIP - xnor/BMXNet-v2)] [![GitHub stars](https://img.shields.io/github/stars/hpi-xnor/BMXNet-v2?style=social)](https://github.com/hpi-xnor/BMXNet-v2)
      • [ICLR
      • [ICLR
      • [ICML - Bit Quantization of Transformer Neural Machine Language Translation Model
      • [ICUS
      • [IEEE J. Emerg. Sel. Topics Circuits Syst. - Chip Systolically Scalable Binary-Weight CNN Inference Engine
      • [IEEE J. Solid-State Circuits - Efficient Reconfigurable Processor for Binary-and Ternary-Weight Neural Networks With Flexible Data Bit Width
      • [IEEE JETC
      • [IEEE TCS.I - Chip Memory
      • [IEEE TCS.I - RAM: Accelerating Binary Neural Networks in High-Throughput SRAM Compute Arrays
      • [IJCAI
      • [IJCAI - Efficient Hashing with Minimizing Quantization Loss
      • [ISOCC
      • [MDPI Electronics
      • [NeurIPS
      • [NeurIPS - bnn-optimization)] [![GitHub stars](https://img.shields.io/github/stars/plumerai/rethinking-bnn-optimization?style=social)](https://github.com/plumerai/rethinking-bnn-optimization)
      • [NeurIPS - differentiable Quantization [[code](https://github.com/csyhhu/MetaQuant)] [![GitHub stars](https://img.shields.io/github/stars/csyhhu/MetaQuant?style=social)](https://github.com/csyhhu/MetaQuant)
      • [NeurIPS
      • [NeurIPS
      • [NeurIPS
      • [NeurIPS
      • [RoEduNet
      • [SiPS
      • [TMM
      • [TMM - Modal Hashing
      • [VLSI-SoC - Efficient Execution of Binary Neural Networks Using Resistive Memories
      • [arXiv - CV/dabnn)] [![GitHub stars](https://img.shields.io/github/stars/JDAI-CV/dabnn?style=social)](https://github.com/JDAI-CV/dabnn)
      • [arXiv
      • [arXiv - aware Knowledge Distillation
      • [arXiv - Binarizing Networks
      • [arXiv
      • [paper
    • 2020

      • [CVPR - Net)] [![GitHub stars](https://img.shields.io/github/stars/htqin/IR-Net?style=social)](https://github.com/htqin/IR-Net)
      • [PR
      • [AAAI - BERT: Hessian Based Ultra Low Precision Quantization of BERT
      • [ACL
      • [COOL CHIPS - DRAM Accelerator Architecture for Binary Neural Network
      • [CVPR - han-lab/apq)] [![GitHub stars](https://img.shields.io/github/stars/mit-han-lab/apq?style=social)](https://github.com/mit-han-lab/apq)
      • [CVPR
      • [CVPR - Point Back-Propagation Training
      • [CVPR
      • [CVPR - Bit Quantization Needs Good Distribution
      • [CVPR - Bit Face Recognition
      • [arXiv
      • [DATE - based computing systems
      • [DATE
      • [DATE - Accelerated Binary Neural Network Inference Engine for Mobile Phones
      • [ECCV
      • [ECCV
      • [ECCV - bitwidth Data Free Quantization [[code](https://github.com/xushoukai/GDFQ)] [![GitHub stars](https://img.shields.io/github/stars/xushoukai/GDFQ?style=social)](https://github.com/xushoukai/GDFQ)
      • [ECCV
      • [ECCV - 4-bit MobileNet Models
      • [ECCV
      • [ECCV
      • [EMNLP
      • [EMNLP - aware Ultra-low Bit BERT [[code](https://github.com/huawei-noah/Pretrained-Language-Model)] [![GitHub stars](https://img.shields.io/github/stars/huawei-noah/Pretrained-Language-Model?style=social)](https://github.com/huawei-noah/Pretrained-Language-Model)
      • [ICASSP
      • [ICET - Efficient Bagged Binary Neural Network Accelerator
      • [ICLR - K1m/BinaryDuo)] [![GitHub stars](https://img.shields.io/github/stars/Hyungjun-K1m/BinaryDuo?style=social)](https://github.com/Hyungjun-K1m/BinaryDuo)
      • [ICLR
      • [ICLR
      • [ICLR - research-code/tree/master/mixed-precision-dnns)] [![GitHub stars](https://img.shields.io/github/stars/sony/ai-research-code?style=social)](https://github.com/sony/ai-research-code)
      • [ICLR - to-Binary Convolutions
      • [ICML - Scale Inference with Anisotropic Vector Quantization
      • [ICML - bit quantization through learnable offsets and better initialization
      • [ICML
      • [ICML - Training Quantization
      • [IEEE Access - Efficient and High Throughput in-Memory Computing Bit-Cell With Excellent Robustness Under Process Variations for Binary Neural Network
      • [IEEE TCS.I - Memory Multi-Bit Multiplication and ACcumulation in 6T SRAM Array
      • [IEEE TCS.II - Efficient Inference Accelerator for Binary Convolutional Neural Networks
      • [IEEE Trans. Electron Devices
      • [IEEE Trans. Magn - Memory Binary Neural Network Accelerator
      • [IJCAI - NAS: Child-Parent Neural Architecture Search for Binary Neural Networks
      • [IJCAI - width Deep Neural Networks
      • [IJCAI
      • [IJCAI - bit Multiply-Accumulate Operations
      • [IJCAI
      • [IJCAI - bit Integer Inference for the Transformer Model
      • [IJCV
      • [ISCAS - Level Binarized Recurrent Neural Network for EEG Signal Classification
      • [ISQED - ASU/BNNPruning)] [![GitHub stars](https://img.shields.io/github/stars/PSCLab-ASU/BNNPruning?style=social)](https://github.com/PSCLab-ASU/BNNPruning)
      • [MICRO - Based NLP Models for Low Latency and Energy Efficient Inference
      • [MLST
      • [NN - performance and large-scale deep neural networks with full 8-bit integers
      • [NeurIPS - Parallel SGD [[code](https://github.com/tabrizian/learning-to-quantize)] [![GitHub stars](https://img.shields.io/github/stars/tabrizian/learning-to-quantize?style=social)](https://github.com/tabrizian/learning-to-quantize)
      • [NeurIPS
      • [NeurIPS - Layer Flow [[code](https://github.com/didriknielsen/pixelcnn_flow)] [![GitHub stars](https://img.shields.io/github/stars/didriknielsen/pixelcnn_flow?style=social)](https://github.com/didriknielsen/pixelcnn_flow)
      • [NeurIPS - kai/eevbnn)] [![GitHub stars](https://img.shields.io/github/stars/jia-kai/eevbnn?style=social)](https://github.com/jia-kai/eevbnn)
      • [NeurIPS
      • [NeurIPS - V2: Hessian Aware trace-Weighted Quantization of Neural Networks
      • [NeurIPS - Analytic Gradient Estimators for Stochastic Binary Networks [[code](https://github.com/shekhovt/PSA-Neurips2020)] [![GitHub stars](https://img.shields.io/github/stars/shekhovt/PSA-Neurips2020?style=social)](https://github.com/shekhovt/PSA-Neurips2020)
      • [NeurIPS - based Scaled Gradient for Model Quantization and Pruning [[code](https://github.com/Jangho-Kim/PSG-pytorch)] [![GitHub stars](https://img.shields.io/github/stars/Jangho-Kim/PSG-pytorch?style=social)](https://github.com/Jangho-Kim/PSG-pytorch)
      • [NeurIPS
      • [NeurIPS
      • [NeurIPS - Bit Weights in Quantized Neural Networks [[code](https://github.com/zhaohui-yang/Binary-Neural-Networks/tree/main/SLB)] [![GitHub stars](https://img.shields.io/github/stars/zhaohui-yang/Binary-Neural-Networks?style=social)](https://github.com/zhaohui-yang/Binary-Neural-Networks)
      • [NeurIPS
      • [Neurocomputing