{"id":58045,"url":"https://github.com/chadHGY/awesome-deep-model-compression","name":"awesome-deep-model-compression","description":"Awesome Deep Model Compression","projects_count":37,"last_synced_at":"2026-08-23T22:00:26.939Z","repository":{"id":166011821,"uuid":"357397975","full_name":"chadHGY/awesome-deep-model-compression","owner":"chadHGY","description":"Awesome Deep Model Compression","archived":false,"fork":false,"pushed_at":"2021-04-13T13:01:57.000Z","size":49,"stargazers_count":3,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2026-07-16T04:03:18.152Z","etag":null,"topics":["awesome-list","deep-learning","model-compression","model-distillation","neural-network","pruning","python","quantization"],"latest_commit_sha":null,"homepage":"","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/chadHGY.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null}},"created_at":"2021-04-13T02:17:34.000Z","updated_at":"2026-03-18T13:35:21.000Z","dependencies_parsed_at":"2024-04-08T01:14:27.080Z","dependency_job_id":"a5df131f-d355-4df4-a848-09e098703794","html_url":"https://github.com/chadHGY/awesome-deep-model-compression","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/chadHGY/awesome-deep-model-compression","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/chadHGY%2Fawesome-deep-model-compression","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/chadHGY%2Fawesome-deep-model-compression/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/chadHGY%2Fawesome-deep-model-compression/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/chadHGY%2Fawesome-deep-model-compression/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/chadHGY","download_url":"https://codeload.github.com/chadHGY/awesome-deep-model-compression/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/chadHGY%2Fawesome-deep-model-compression/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":36271787,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-07-20T02:08:10.276Z","status":"online","status_checked_at":"2026-08-04T02:00:06.901Z","response_time":57,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"created_at":"2024-04-08T00:00:27.051Z","updated_at":"2026-08-23T22:00:26.939Z","primary_language":null,"list_of_lists":false,"displayable":true,"categories":["Tools","Articles","Papers"],"sub_categories":["Hard-ware Integration","Libraries","Blogs","Pruning","Cross Platform"],"readme":"# Awesome Deep Model Compression \n[![Awesome](https://awesome.re/badge.svg)](https://awesome.re) [![hackmd-github-sync-badge](https://hackmd.io/uDS93NOpStaNuKB2Y1KXLQ/badge)](https://hackmd.io/uDS93NOpStaNuKB2Y1KXLQ)\n\nA useful list of Deep Model Compression related research papers, articles, tutorials, libraries, tools and more.  \nCurrently the Repos are additional given tags either [Pytorch/TF]. To quickly find hands-on Repos in your commonly used framework, please Ctrl+F to get start :smiley:\n\n\n\n## Contents\n- [Papers](#papers)\n  - [General](#general)\n  - [Architecture](#architecture)\n  - [Quantization](#quantization)\n  - [Binarization](#binarization)\n  - [Pruning](#pruning)\n  - [Distillation](#distillation)\n  - [Low Rank Approximation](#low-rank-approximation)\n- [Articles](#articles)\n  - [Blogs](#blogs)\n- [Tools](#tools)\n  - [Libraries](#libraries)\n  - [Cross Platform](#cross-platform)\n  - [Hard-ware Integration](#hard-ware-integration)\n---\n\n\n## Papers\n### General\n\n### Architecture\n\n### Quantization\n\n### Binarization\n\n### Pruning\n- The Lottery Ticket Hypothesis | ICLR, 2019, Google | [Paper](https://openreview.net/pdf?id=rJl-b3RcF7) | [Code](https://github.com/google-research/lottery-ticket-hypothesis)\n### Distillation\n\n### Low Rank Approximation\n\n---\n## Articles\n### Blogs\n- [Pruning deep neural networks to make them fast and small](https://jacobgil.github.io/deeplearning/pruning-deep-learning) [Pytorch] By using pruning a VGG-16 based Dogs-vs-Cats classifier is made x3 faster and x4 smaller.\n- [All The Ways You Can Compress BERT](http://mitchgordon.me/machine/learning/2019/11/18/all-the-ways-to-compress-BERT.html) - An overview of different compression methods for large NLP models (BERT) based on different characteristics and compares their results.\n- [Deep Learning Model Compression](https://rachitsingh.com/deep-learning-model-compression/) methods.\n- [Do We Really Need Model Compression](http://mitchgordon.me/machine/learning/2020/01/13/do-we-really-need-model-compression.html) in the future?\n\n---\n## Tools\n### Libraries\n- [torch.nn.utils.prune](https://pytorch.org/tutorials/intermediate/pruning_tutorial.html) [Pytorch]  \nPytorch official supported sparsify neural networks and custom pruning technique.\n- [Neural Network Intelligence](https://nni.readthedocs.io/en/v1.6/model_compression.html)[Pytorch/TF]\n[![Star on GitHub](https://img.shields.io/github/stars/microsoft/nni.svg?style=social)](https://github.com/microsoft/nni)  \nThere are some popular model compression algorithms built-in in NNI. Users could further use NNI’s auto tuning power to find the best compressed model, which is detailed in Auto Model Compression.\n- [Condensa](https://github.com/NVlabs/condensa) [Pytorch]\n[![Star on GitHub](https://img.shields.io/github/stars/NVlabs/condensa.svg?style=social)](https://github.com/NVlabs/condensa)  \nA Programming System for Neural Network Compression. | [paper](https://arxiv.org/pdf/1911.02497.pdf)\n- [IntelLabs distiller](https://github.com/IntelLabs/distiller) [Pytorch] [![Star on GitHub](https://img.shields.io/github/stars/IntelLabs/distiller.svg?style=social)](https://github.com/IntelLabs/distiller)  \nNeural Network Distiller by Intel AI Lab: a Python package for neural network compression research. | [Documentation](https://intellabs.github.io/distiller/)\n- [Torch-Pruning](https://github.com/VainF/Torch-Pruning)[Pytorch]\n[![Star on GitHub](https://img.shields.io/github/stars/VainF/Torch-Pruning.svg?style=social)](https://github.com/VainF/Torch-Pruning)  \nA pytorch toolkit for structured neural network pruning and layer dependency. \n- [CompressAI](https://github.com/InterDigitalInc/CompressAI) [Pytorch]\n[![Star on GitHub](https://img.shields.io/github/stars/InterDigitalInc/CompressAI.svg?style=social)](https://github.com/InterDigitalInc/CompressAI)  \nA PyTorch library and evaluation platform for end-to-end compression research.\n- [Model Compression](https://github.com/j-marple-dev/model_compression)[Pytorch] \n[![Star on GitHub](https://img.shields.io/github/stars/j-marple-dev/model_compression.svg?style=social)](https://github.com/j-marple-dev/model_compression)  \nA onestop pytorch model compression repo. | [Reposhub](https://reposhub.com/python/deep-learning/j-marple-dev-model_compression.html)\n- [TensorFlow Model Optimization Toolkit](https://github.com/tensorflow/model-optimization) [TF]\n[![Star on GitHub](https://img.shields.io/github/stars/tensorflow/model-optimization.svg?style=social)](https://github.com/tensorflow/model-optimization)  \nAccompanied blog post, [TensorFlow Model Optimization Toolkit — Pruning API](https://medium.com/tensorflow/tensorflow-model-optimization-toolkit-pruning-api-42cac9157a6a?linkId=67380711) \n- [XNNPACK](https://github.com/google/xnnpack) \n[![Star on GitHub](https://img.shields.io/github/stars/google/xnnpack.svg?style=social)](https://github.com/google/xnnpack)  \nXNNPACK is a highly optimized library of floating-point neural network inference operators for ARM, WebAssembly, and x86 (SSE2 level) platforms. It's a based on QNNPACK library. However, unlike QNNPACK, XNNPACK focuses entirely on floating-point operators. \n\n### Cross Platform\n- [Loading a TorchScript Model in C++](https://pytorch.org/tutorials/advanced/cpp_export.html) [Pytorch x C++]  \nFrom an existing Python model to a serialized representation that can be loaded and executed purely from C++, with no dependency on Python.\n- [Open Neural Network Exchange (ONNX)](https://github.com/onnx/tutorials)[Pytorch, TF, Keras...etc]\n[![Star on GitHub](https://img.shields.io/github/stars/onnx/onnx.svg?style=social)](https://github.com/onnx/onnx)  \nAn open standard format for representing machine learning models. \n\n\n### Hard-ware Integration\n* [TensorRT (NVIDIA)](https://developer.nvidia.com/tensorrt) [Pytorch, TF,Keras ...etc] \u003cbr\u003e\n\u003cimg width=\"400\" src=\"https://i.imgur.com/lvNIh5g.png\"\u003e \u003cbr\u003e\u003cbr\u003e\n    * [torch2trt](https://github.com/NVIDIA-AI-IOT/torch2trt) [Pytorch] [![Star on GitHub](https://img.shields.io/github/stars/NVIDIA-AI-IOT/torch2trt.svg?style=social)](https://github.com/NVIDIA-AI-IOT/torch2trt)  \n    An easy to use PyTorch to TensorRT converter\n    * [How to Convert a Model from PyTorch to TensorRT and Speed Up Inference](https://learnopencv.com/how-to-convert-a-model-from-pytorch-to-tensorrt-and-speed-up-inference/) [Pytorch] \u003cimg width=\"300\" src=\"https://i.imgur.com/7lxhbzQ.png\"\u003e\n\n* [TVM (Apache)](https://github.com/apache/tvm) [[Pytorch](https://tvm.apache.org/docs/tutorials/frontend/from_pytorch.html), [TF](https://tvm.apache.org/docs/tutorials/frontend/from_tensorflow.html#sphx-glr-tutorials-frontend-from-tensorflow-py)] [![Star on GitHub](https://img.shields.io/github/stars/apache/tvm.svg?style=social)](https://github.com/apache/tvm)  \nOpen deep learning compiler stack for cpu, gpu and specialized accelerators\n\u003cimg width=\"500\" src=\"https://raw.githubusercontent.com/hogepodge/web-data/c339ebbbae41f3762873147c1e920a53a08963dd/images/getting_started/overview.png\"\u003e\n\n* [Pytorch Glow](https://github.com/pytorch/glow) [![Star on GitHub](https://img.shields.io/github/stars/pytorch/glow.svg?style=social)](https://github.com/pytorch/glow)  \nGlow is a machine learning compiler and execution engine for hardware accelerators. It is designed to be used as a backend for high-level machine learning frameworks. The compiler is designed to allow state of the art compiler optimizations and code generation of neural network graphs.  \n\u003cimg width=\"400\" src=\"https://i.imgur.com/bpQcHUO.png\"\u003e\n\n* [CoreML (Apple)](https://github.com/apple/coremltools) [Pytorch,TF,Keras,SKLearn ...etc] [![Star on GitHub](https://img.shields.io/github/stars/apple/coremltools.svg?style=social)](https://github.com/apple/coremltools)  \nCore ML provides a unified representation for all models. Your app uses Core ML APIs and user data to make predictions, and to train or fine-tune models, all on the user’s device.  \n[Introduction](https://developer.apple.com/documentation/coreml)  \n\u003cimg width=\"400\" src=\"https://docs-assets.developer.apple.com/published/65b8e13531/e3663268-5db4-42c9-a7f0-2114920a9f1f.png\"\u003e  \n\n\n* [Tensorflow Lite (Google)](https://www.tensorflow.org/lite) [TF]  \nAn open source deep learning framework for on-device inference.\n\u003cimg width=\"400\" src=\"https://i.imgur.com/kcXIA5A.png\"\u003e  \n\n* [~~Intel Nervana Neon~~](https://github.com/NervanaSystems/neon) [Deprecated] [![Star on GitHub](https://img.shields.io/github/stars/NervanaSystems/neon.svg?style=social)](https://github.com/NervanaSystems/neon)  ","projects_url":"https://awesome.ecosyste.ms/api/v1/lists/chadhgy%2Fawesome-deep-model-compression/projects"}