sparsity

There are 135 repositories under sparsity topic.

  • intel/neural-compressor

    SOTA low-bit LLM quantization (INT8/FP8/INT4/FP4/NF4) & sparsity; leading model compression techniques on TensorFlow, PyTorch, and ONNX Runtime

    Language:Python2.5k33219282

  • pytorch/ao

    PyTorch native quantization and sparsity for training and inference

    Language:Python2.4k45586336
  • sparseml

    neuralmagic/sparseml

    Libraries for applying sparsification recipes to neural networks with a few lines of code, enabling faster and smaller models

    Language:Python2.1k47212157

  • vllm-project/llm-compressor

    Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM

    Language:Python1.9k23389228

  • PaddlePaddle/PaddleSlim

    PaddleSlim is an open-source library for deep model compression and architecture search.

    Language:Python1.6k90560350

  • tensorflow/model-optimization

    A toolkit to optimize ML models for deployment for Keras and TensorFlow, including quantization and pruning.

    Language:Python1.6k118367331

  • openvinotoolkit/nncf

    Neural Network Compression Framework for enhanced OpenVINO™ inference

    Language:Python1.1k31363257

  • Eric-mingjie/network-slimming

    Network Slimming (Pytorch) (ICCV 2017)

    Language:Python9141393213

  • Bobo-y/flexible-yolov5

    More readable and flexible yolov5 with more backbone(gcn, resnet, shufflenet, moblienet, efficientnet, hrnet, swin-transformer, etc) and (cbam，dcn and so on), and tensorrt

    Language:Python67910146119

  • FMInference/H2O

    [NeurIPS'23] H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.

    Language:Python47354265

  • wenwei202/caffe

    Caffe for Sparse and Low-rank Deep Neural Networks

    Language:C++3813535134

  • intel/neural-speed

    An innovative library for efficient LLM inference via low-bit quantization

    Language:C++34874738

  • mehtadushy/SelecSLS-Pytorch

    Reference ImageNet implementation of SelecSLS CNN architecture proposed in the SIGGRAPH 2020 paper "XNect: Real-time Multi-Person 3D Motion Capture with a Single RGB Camera". The repository also includes code for pruning the model based on implicit sparsity emerging from adaptive gradient descent methods, as detailed in the CVPR 2019 paper "On implicit filter level sparsity in Convolutional Neural Networks".

    Language:Python339181445

  • bwohlberg/sporco

    Sparse Optimisation Research Code

    Language:Python272162239

  • dcmocanu/sparse-evolutionary-artificial-neural-networks

    Always sparse. Never dense. But never say never. A Sparse Training repository for the Adaptive Sparse Connectivity concept and its algorithmic instantiation, i.e. Sparse Evolutionary Training, to boost Deep Learning scalability on various aspects (e.g. memory and computational time efficiency, representation and generalization power).

    Language:Python24923264

  • SYSU-SAIL/SMSR

    [CVPR 2021] Exploring Sparsity in Image Super-Resolution for Efficient Inference

    Language:Python23972830

  • IntelLabs/SkimCaffe

    Caffe for Sparse Convolutional Neural Network

    Language:C++237252164

  • vene/sparse-structured-attention

    Sparse and structured neural attention mechanisms

    Language:Python2246836

  • jack-willturner/deep-compression

    Learning both Weights and Connections for Efficient Neural Networks https://arxiv.org/abs/1506.02626

    Language:Jupyter Notebook1773638

  • lucaslie/torchprune

    A research library for pytorch-based neural network pruning, compression, and more.

    Language:Shell16251225

  • NVIDIA-AI-IOT/clip-distillation

    Zero-label image classification via OpenCLIP knowledge distillation

    Language:Python1347314

  • FasterDecoding/TEAL

    Language:Python1223105

  • openvinotoolkit/mmdetection

    OpenVINO Training Extensions Object Detection

    Language:Python9372130

  • RAIVNLab/STR

    Soft Threshold Weight Reparameterization for Learnable Sparsity

    Language:Python916811

  • OpenSparseLLMs/LLaMA-MoE-v2

    🚀 LLaMA-MoE v2: Exploring Sparsity of LLaMA from Perspective of Mixture-of-Experts with Post-Training

    Language:Python782311

  • wenwei202/iss-rnns

    Sparse Recurrent Neural Networks -- Pruning Connections and Hidden Sizes (TensorFlow)

    Language:Python7441121

  • luuyin/OWL

    Official Pytorch Implementation of "Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsity"

    Language:Python622108

  • vene/pyowl

    Ordered Weighted L1 regularization for classification and regression in Python

    Language:Python524310

  • adrhill/SparseConnectivityTracer.jl

    Fast operator-overloading Jacobian & Hessian sparsity detection.

    Language:Julia503885

  • rajmic/declipping2020_codes

    Codes and data coming with article "A Survey and an Extensive Evaluation of Popular Audio Declipping Methods", and others closely related

    Language:MATLAB484111

  • satabios/sconce

    E2E AutoML Model Compression Package

    Language:Jupyter Notebook47114

  • Shiweiliuiiiiiii/In-Time-Over-Parameterization

    [ICML 2021] "Do We Actually Need Dense Over-Parameterization? In-Time Over-Parameterization in Sparse Training" by Shiwei Liu, Lu Yin, Decebal Constantin Mocanu, Mykola Pechenizkiy

    Language:Python45216

  • SIP-AAU/Magni

    A package for AFM image reconstruction and compressed sensing in general

    Language:Python4215410

  • MingSun-Tse/Why-the-State-of-Pruning-so-Confusing

    [Preprint] Why is the State of Neural Network Pruning so Confusing? On the Fairness, Comparison Setup, and Trainability in Network Pruning

    40321

  • VITA-Group/Sparsity-Win-Robust-Generalization

    [ICLR 2022] "Sparsity Winning Twice: Better Robust Generalization from More Efficient Training" by Tianlong Chen*, Zhenyu Zhang*, Pengjun Wang*, Santosh Balachandra*, Haoyu Ma*, Zehao Wang, Zhangyang Wang

    Language:Python39722

  • RabadanLab/randomly

    A Library for Denoising Single-Cell Data with Random Matrix Theory

    Language:Jupyter Notebook3716410