Git Stars Git Stars

#pytorch Repositories

1,936
Total Repositories
7.7M
Total Stars
3,996
Avg Stars/Repo

1,936 repositories total

801
microsoft/mup

maximal update parametrization (ยตP)

microsoft
โญ 1,649 Jupyter Notebook ๐Ÿ‘ค microsoft Organization ๐Ÿ• Updated 2024-07-17 ๐Ÿ“… Created 2021-11-02
802
rwightman/efficientdet-pytorch

A PyTorch impl of EfficientDet faithful to the original Google impl w/ ported weights

rwightman
โญ 1,649 Python ๐Ÿ‘ค rwightman User ๐Ÿ• Updated 2024-08-29 ๐Ÿ“… Created 2020-03-26
803
ymcui/Chinese-XLNet

Pre-Trained Chinese XLNet (Chinese XLNet Pre-trained Model)

ymcui
โญ 1,647 Python ๐Ÿ‘ค ymcui User ๐Ÿ• Updated 2026-04-19 ๐Ÿ“… Created 2019-07-15
804
pq-yang/MatAnyone

[CVPR 2025] MatAnyone: Stable Video Matting with Consistent Memory Propagation

pq-yang
โญ 1,646 Python ๐Ÿ‘ค pq-yang User ๐Ÿ• Updated 2026-03-04 ๐Ÿ“… Created 2025-02-02
806
CoinCheung/BiSeNet

Add bisenetv2. My implementation of BiSeNet

CoinCheung
โญ 1,645 Python ๐Ÿ‘ค CoinCheung User ๐Ÿ• Updated 2026-11-11 ๐Ÿ“… Created 2018-11-29
807
ZFTurbo/Music-Source-Separation-Training

Repository for training models for music source separation.

ZFTurbo
โญ 1,644 Python ๐Ÿ‘ค ZFTurbo User ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2023-11-06
808
ZrrSkywalker/Personalize-SAM

Personalize Segment Anything Model (SAM) with 1 shot in 10 seconds

ZrrSkywalker
โญ 1,642 Python ๐Ÿ‘ค ZrrSkywalker User ๐Ÿ• Updated 2024-07-22 ๐Ÿ“… Created 2023-05-04
809
yoshitomo-matsubara/torchdistill

A coding-free framework built on PyTorch for reproducible deep learning studies. PyTorch Ecosystem. ๐Ÿ† 28 knowledge distillation methods presented at TPAMI, CVPR, ICLR, ECCV, NeurIPS, ICCV, AAAI, etc. have been implemented so far. ๐ŸŽ Trained models, training logs, and configurations are available to ensure reproducibility and benchmarking.

yoshitomo-matsubara
โญ 1,636 Python ๐Ÿ‘ค yoshitomo-matsubara User ๐Ÿ• Updated 2026-11-19 ๐Ÿ“… Created 2019-12-18
810
jiaweizzhao/GaLore

GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection

jiaweizzhao
โญ 1,635 Python ๐Ÿ‘ค jiaweizzhao User ๐Ÿ• Updated 2024-10-28 ๐Ÿ“… Created 2024-03-07
811
kan-bayashi/ParallelWaveGAN

Unofficial Parallel WaveGAN (+ MelGAN & Multi-band MelGAN & HiFi-GAN & StyleMelGAN) with Pytorch

kan-bayashi
โญ 1,634 Jupyter Notebook ๐Ÿ‘ค kan-bayashi User ๐Ÿ• Updated 2024-04-22 ๐Ÿ“… Created 2019-10-29
812
RightNow-AI/autokernel

Autoresearch for GPU kernels. Give it any PyTorch model, go to sleep, wake up to optimized Triton kernels.

RightNow-AI
โญ 1,633 Python ๐Ÿ‘ค RightNow-AI Organization ๐Ÿ• Updated 2026-11-18 ๐Ÿ“… Created 2026-03-11
813
mhamilton723/FeatUp

Official code for "FeatUp: A Model-Agnostic Frameworkfor Features at Any Resolution" ICLR 2024

mhamilton723
โญ 1,620 Jupyter Notebook ๐Ÿ‘ค mhamilton723 User ๐Ÿ• Updated 2024-06-28 ๐Ÿ“… Created 2024-02-22
814
pypose/pypose

A library for differentiable robotics on manifolds.

pypose
โญ 1,620 Python ๐Ÿ‘ค pypose Organization ๐Ÿ• Updated 2026-11-06 ๐Ÿ“… Created 2021-11-11
815
Drexubery/ViewCrafter

[TPAMI 2025] ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis

Drexubery
โญ 1,617 Python ๐Ÿ‘ค Drexubery User ๐Ÿ• Updated 2025-12-13 ๐Ÿ“… Created 2024-07-22
816
Tencent-Hunyuan/AuK

AuK: An Open-Source Foundational Model for Speech Generation and Editing

Tencent-Hunyuan
โญ 1,615 Python ๐Ÿ‘ค Tencent-Hunyuan Organization ๐Ÿ• Updated 2026-11-19 ๐Ÿ“… Created 2026-08-19
817
QwenAudio/Fun-ASR

Fun-ASR speech recognition models, with native Hugging Face Transformers support for Fun-ASR-Nano and separate FunASR, vLLM and llama.cpp deployment paths.

QwenAudio
โญ 1,614 C ๐Ÿ‘ค QwenAudio Organization ๐Ÿ• Updated 2026-11-20 ๐Ÿ“… Created 2025-12-15
818
ARISE-Initiative/robomimic

robomimic: A Modular Framework for Robot Learning from Demonstration

ARISE-Initiative
โญ 1,607 Python ๐Ÿ‘ค ARISE-Initiative Organization ๐Ÿ• Updated 2026-08-09 ๐Ÿ“… Created 2021-08-06
819
pytorch/FBGEMM

FB (Facebook) + GEMM (General Matrix-Matrix Multiplication) - https://code.fb.com/ml-applications/fbgemm/

pytorch
โญ 1,604 C++ ๐Ÿ‘ค pytorch Organization ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2018-09-24
820
Tencent/DepthCrafter

[CVPR 2025 Highlight] DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videos

Tencent
โญ 1,601 Python ๐Ÿ‘ค Tencent Organization ๐Ÿ• Updated 2025-11-30 ๐Ÿ“… Created 2024-09-04
821
Xilinx/brevitas

Brevitas: neural network quantization in PyTorch

Xilinx
โญ 1,601 Python ๐Ÿ‘ค Xilinx Organization ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2018-07-10
822
zju3dv/EasyVolcap

[SIGGRAPH Asia 2023 (Technical Communications)] EasyVolcap: Accelerating Neural Volumetric Video Research

zju3dv
โญ 1,600 Python ๐Ÿ‘ค zju3dv Organization ๐Ÿ• Updated 2026-09-15 ๐Ÿ“… Created 2023-12-07
โญ 1,599 Python ๐Ÿ‘ค databricks Organization ๐Ÿ• Updated 2026-03-25 ๐Ÿ“… Created 2023-01-26
824
jeffffffli/HybrIK

Official code of "HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimation", CVPR 2021

jeffffffli
โญ 1,599 Python ๐Ÿ‘ค jeffffffli User ๐Ÿ• Updated 2025-01-08 ๐Ÿ“… Created 2020-11-30
825
facebookresearch/DomainBed

DomainBed is a suite to test domain generalization algorithms

facebookresearch
โญ 1,596 Python ๐Ÿ‘ค facebookresearch Organization ๐Ÿ• Updated 2025-12-16 ๐Ÿ“… Created 2020-06-29
826
microsoft/Semi-supervised-learning

A Unified Semi-Supervised Learning Codebase (NeurIPS'22)

microsoft
โญ 1,590 Python ๐Ÿ‘ค microsoft Organization ๐Ÿ• Updated 2026-10-04 ๐Ÿ“… Created 2022-05-05
827
decoderesearch/SAELens

Training Sparse Autoencoders on Language Models

decoderesearch
โญ 1,588 Python ๐Ÿ‘ค decoderesearch Organization ๐Ÿ• Updated 2026-11-20 ๐Ÿ“… Created 2023-11-29
828
bioinf-jku/SNNs

Tutorials and implementations for "Self-normalizing networks"

bioinf-jku
โญ 1,588 Jupyter Notebook ๐Ÿ‘ค bioinf-jku Organization ๐Ÿ• Updated 2026-05-12 ๐Ÿ“… Created 2017-06-08
829
ELS-RD/kernl

Kernl lets you run PyTorch transformer models several times faster on GPU with a single line of code, and is designed to be easily hackable.

ELS-RD
โญ 1,584 Jupyter Notebook ๐Ÿ‘ค ELS-RD Organization ๐Ÿ• Updated 2024-02-16 ๐Ÿ“… Created 2022-08-05
830
lufficc/SSD

High quality, fast, modular reference implementation of SSD in PyTorch

lufficc
โญ 1,584 Python ๐Ÿ‘ค lufficc User ๐Ÿ• Updated 2024-01-26 ๐Ÿ“… Created 2018-12-06
831
rwightman/gen-efficientnet-pytorch

Pretrained EfficientNet, EfficientNet-Lite, MixNet, MobileNetV3 / V2, MNASNet A1 and B1, FBNet, Single-Path NAS

rwightman
โญ 1,583 Python ๐Ÿ‘ค rwightman User ๐Ÿ• Updated 2024-06-13 ๐Ÿ“… Created 2019-05-11
832
vturrisi/solo-learn

solo-learn: a library of self-supervised methods for visual representation learning powered by Pytorch Lightning

vturrisi
โญ 1,582 Python ๐Ÿ‘ค vturrisi User ๐Ÿ• Updated 2026-10-12 ๐Ÿ“… Created 2021-03-06
833
sniklaus/3d-ken-burns

an implementation of 3D Ken Burns Effect from a Single Image using PyTorch

sniklaus
โญ 1,579 Python ๐Ÿ‘ค sniklaus User ๐Ÿ• Updated 2026-11-19 ๐Ÿ“… Created 2019-11-19
834
ai-forever/ghost

A new one shot face swap approach for image and video domains

ai-forever
โญ 1,578 Python ๐Ÿ‘ค ai-forever Organization ๐Ÿ• Updated 2025-02-25 ๐Ÿ“… Created 2021-12-13
835
mit-han-lab/smoothquant

[ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models

mit-han-lab
โญ 1,576 Python ๐Ÿ‘ค mit-han-lab Organization ๐Ÿ• Updated 2024-07-12 ๐Ÿ“… Created 2022-11-17
836
BloodAxe/pytorch-toolbelt

PyTorch extensions for fast R&D prototyping and Kaggle farming

BloodAxe
โญ 1,575 Python ๐Ÿ‘ค BloodAxe User ๐Ÿ• Updated 2025-10-09 ๐Ÿ“… Created 2019-03-15
837
mosaicml/streaming

A Data Streaming Library for Efficient Neural Network Training

mosaicml
โญ 1,574 Python ๐Ÿ‘ค mosaicml Organization ๐Ÿ• Updated 2026-11-03 ๐Ÿ“… Created 2022-06-09
838
facebookresearch/fast3r

[CVPR 2025] Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass

facebookresearch
โญ 1,573 Python ๐Ÿ‘ค facebookresearch Organization ๐Ÿ• Updated 2025-05-07 ๐Ÿ“… Created 2024-10-15
839
Soul-AILab/SoulX-FlashTalk

SoulX-FlashTalk is the first 14B model to achieve sub-second start-up latency (0.87s) while maintaining a real-time throughput of 32 FPS on an 8xH800 node.

Soul-AILab
โญ 1,572 Python ๐Ÿ‘ค Soul-AILab Organization ๐Ÿ• Updated 2026-07-30 ๐Ÿ“… Created 2025-12-25
840
dauparas/ProteinMPNN

Code for the ProteinMPNN paper

dauparas
โญ 1,567 Jupyter Notebook ๐Ÿ‘ค dauparas User ๐Ÿ• Updated 2024-08-14 ๐Ÿ“… Created 2022-05-26
841
ZeyueT/AudioX

[ICLR 2026] Repository of AudioX

ZeyueT
โญ 1,559 Python ๐Ÿ‘ค ZeyueT User ๐Ÿ• Updated 2026-03-10 ๐Ÿ“… Created 2025-03-13
842
photosynthesis-team/piq

Measures and metrics for image2image tasks. PyTorch.

photosynthesis-team
โญ 1,555 Python ๐Ÿ‘ค photosynthesis-team Organization ๐Ÿ• Updated 2024-05-12 ๐Ÿ“… Created 2019-12-19
843
DeepGraphLearning/torchdrug

A powerful and flexible machine learning platform for drug discovery

DeepGraphLearning
โญ 1,554 Python ๐Ÿ‘ค DeepGraphLearning Organization ๐Ÿ• Updated 2024-08-12 ๐Ÿ“… Created 2021-08-10
844
kumar-shridhar/PyTorch-BayesianCNN

Bayesian Convolutional Neural Network with Variational Inference based on Bayes by Backprop in PyTorch.

kumar-shridhar
โญ 1,554 Python ๐Ÿ‘ค kumar-shridhar User ๐Ÿ• Updated 2024-04-19 ๐Ÿ“… Created 2018-07-27
โญ 1,548 Python ๐Ÿ‘ค kijai User ๐Ÿ• Updated 2025-08-07 ๐Ÿ“… Created 2024-08-05
846
DiffEqML/torchdyn

A PyTorch library entirely dedicated to neural differential equations, implicit models and related numerical methods

DiffEqML
โญ 1,548 Jupyter Notebook ๐Ÿ‘ค DiffEqML Organization ๐Ÿ• Updated 2024-05-02 ๐Ÿ“… Created 2020-04-27
847
AIFengheshu/Plug-play-modules

The most comprehensive plug-and-play modules for the entire network in 2025, shared for free! CVPR2025, AAAI2025, ICLR2025, TNNLS2025, arXiv2025...... Covers all fields of artificial intelligence (machine learning, deep learning, etc.), suitable for image classification, object detection, instance segmentation, semantic segmentation, panoptic segmentation, pose estimation, medical image segmentation, video object segmentation, image matting, image editing, single object tracking, multiple object tracking, person re-identification, RGBT, image denoising, rain removal, fog removal, shadow removal, blur removal, super-resolution, reflection removal, moirรฉ pattern removal, image restoration, image inpainting, hyperspectral image restoration, image fusion, image colorization, high dynamic range imaging, video and image compression, 3D point clouds, 3D object detection, 3D semantic segmentation, 3D pose estimation, and various other computer vision and image processing tasks, as well as natural language processing, large language models, multimodal, and other AI-related tasks. Continuously updating......

AIFengheshu
โญ 1,547 Python ๐Ÿ‘ค AIFengheshu User ๐Ÿ• Updated 2025-05-24 ๐Ÿ“… Created 2024-10-09
848
Tencent/TurboTransformers

a fast and user-friendly runtime for transformer inference (Bert, Albert, GPT2, Decoders, etc) on CPU and GPU.

Tencent
โญ 1,546 C++ ๐Ÿ‘ค Tencent Organization ๐Ÿ• Updated 2025-07-18 ๐Ÿ“… Created 2020-04-20
849
kyutai-labs/hibiki

Hibiki is a model for streaming speech translation (also known as simultaneous translation). Unlike offline translationโ€”where one waits for the end of the source utterance to start translating--- Hibiki adapts its flow to accumulate just enough context to produce a correct translation in real-time, chunk by chunk.

kyutai-labs
โญ 1,540 Rust ๐Ÿ‘ค kyutai-labs Organization ๐Ÿ• Updated 2026-09-09 ๐Ÿ“… Created 2025-02-04
850
AnswerDotAI/fsdp_qlora

Training LLMs with QLoRA + FSDP

AnswerDotAI
โญ 1,534 Jupyter Notebook ๐Ÿ‘ค AnswerDotAI Organization ๐Ÿ• Updated 2024-11-09 ๐Ÿ“… Created 2024-01-14