sparsity

Here are 143 public repositories matching this 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

sparsity pruning quantization knowledge-distillation auto-tuning int8 low-precision quantization-aware-training post-training-quantization awq int4 large-language-models gptq smoothquant sparsegpt fp4 mxformat

Updated Jun 13, 2025
Python

neuralmagic / sparseml

Star

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

nlp sparsity tensorflow keras pytorch deep-learning-algorithms image-classification deep-learning-library pruning object-detection transfer-learning automl computer-vision-algorithms onnx deep-learning-models sparsification pruning-algorithms smaller-models sparsification-recipes

Updated Jun 2, 2025
Python

pytorch / ao

Star

PyTorch native quantization and sparsity for training and inference

training sparsity cuda inference optimizer pytorch transformer offloading llama quantization mx brrr dtypes float8

Updated Jun 13, 2025
Python

PaddlePaddle / PaddleSlim

Star

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

sparsity compression detection transformer segmentation pruning quantization nas bert tensorrt distillation ernie yolov5 yolov6 yolov7

Updated Dec 4, 2024
Python

tensorflow / model-optimization

Star

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

machine-learning sparsity compression deep-learning tensorflow optimization keras ml pruning quantization model-compression quantized-training quantized-neural-networks quantized-networks

Updated Feb 10, 2025
Python

vllm-project / llm-compressor

Sponsor

Star

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

sparsity compression quantization

Updated Jun 13, 2025
Python

openvinotoolkit / nncf

Star

Neural Network Compression Framework for enhanced OpenVINO™ inference

nlp sparsity compression deep-learning tensorflow transformers pytorch classification pruning object-detection quantization semantic-segmentation bert onnx openvino mixed-precision-training quantization-aware-training llm genai

Updated Jun 12, 2025
Python

Eric-mingjie / network-slimming

Star

Network Slimming (Pytorch) (ICCV 2017)

sparsity deep-learning pytorch convolutional-neural-networks channel-pruning

Updated Nov 6, 2020
Python

Bobo-y / flexible-yolov5

Star

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

sparsity backbone pytorch resnet object-detection gcn tensorrt neck qat shufflenet yolov3 cbam hrnet dcnv2 yolov5 moblienet swin-transformer triton-server ptq

Updated Aug 19, 2024
Python

FMInference / H2O

Star

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

sparsity high-throughput heavy-hitters kv-cache gpt-3 large-language-models

Updated Aug 1, 2024
Python

wenwei202 / caffe

Star

Caffe for Sparse and Low-rank Deep Neural Networks

deep-neural-networks sparsity acceleration compression caffe low-rank-approximation sparse-convolution

Updated Mar 8, 2020
C++

intel / neural-speed

Star

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

Updated Aug 30, 2024
C++

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 i…

sparsity deep-learning efficient cnn pytorch imagenet pruning siggraph pytorch-implementation cvpr2019 efficient-architectures

Updated Jul 23, 2020
Python

bwohlberg / sporco

Star

Sparse Optimisation Research Code

python sparsity optimization cuda admm sparse-coding dictionary-learning optimization-algorithms robust-pca fista convolutional-sparse-coding total-variation sparse-representations convolutional-dictionary-learning total-variation-minimization plug-and-play-priors

Updated Jan 17, 2025
Python

dcmocanu / sparse-evolutionary-artificial-neural-networks

Star

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).