Popular GitHub Repositories for Pruning

Sparsity-aware deep learning inference runtime for CPUs

A curated list of neural network pruning resources.

AIMET is a library that provides advanced quantization and compression techniques for trained neural network models.

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

OpenMMLab Model Compression Toolbox and Benchmark.

Practical course about Large Language Models.

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

[NeurIPS 2023] LLM-Pruner: On the Structural Pruning of Large Language Models. Support Llama-3/3.1, Llama-2, LLaMA, BLOOM, Vicuna, Baichuan, TinyLlama, etc.

PyTorch Implementation of [1611.06440] Pruning Convolutional Neural Networks for Resource Efficient Inference

Embedded and mobile deep learning research resources

A Pytorch Knowledge Distillation library for benchmarking and extending works in the domains of Knowledge Distillation, Pruning, and Quantization.

[ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning

Awesome machine learning model compression research papers, quantization, tools, and learning material.

? Optimum Intel: Accelerate inference with Intel optimization tools

YOLO ModelCompression MultidatasetTraining

A PyTorch-based model pruning toolkit for pre-trained language models

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".

A model compression and acceleration toolbox based on pytorch.

ML model optimization product to accelerate inference.

OTOv1-v3, NeurIPS, ICLR, TMLR, DNN Training, Compression, Structured Pruning, Erasing Operators, CNN, Diffusion, LLM