1Comfy-Org / ComfyUI
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.
+1,555 stars
from 142,930 · score 7.35
Trending repositories
Ranked by Attention Score: stars gained over the last 7 complete days
1–100 of 101 by Attention Score · Oct 27, 2026 – Nov 2, 2026 (UTC)
2vllm-project / vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
+593 stars
from 95,485 · score 6.39
3NandhaKishorM / laya
Non-autoregressive System 1 decision engine. Typed choice, score and yes/no decisions over any text in a single forward pass, in 100+ languages, with a router that picks the right checkpoint per request.
+511 stars
from 34,302 · score 6.24
4OpenBMB / VoxCPM
VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning
+353 stars
from 40,590 · score 5.87
5kornia / kornia
🐍 Geometric Computer Vision Library for Spatial AI
+329 stars
from 11,447 · score 5.80
6huggingface / transformers
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
+259 stars
from 168,161 · score 5.56
7ultralytics / ultralytics
Ultralytics YOLO27, YOLO26, YOLO11, YOLOv8 — object detection, instance segmentation, semantic segmentation, image classification, pose estimation, object tracking
+188 stars
from 62,830 · score 5.24
8aa1143 / NamiGPT
零基础入门大模型（LLM）的基础教程：从零手写 GPT-2，一行行看懂大模型是怎么工作的 | Build GPT-2 from scratch in PyTorch, step by step
+175 stars
from 0 · score 5.17
9GeeeekExplorer / nano-vllm
Nano vLLM
+128 stars
from 16,125 · score 4.86
10Anjok07 / ultimatevocalremovergui
GUI for a Vocal Remover that uses Deep Neural Networks.
+115 stars
from 26,783 · score 4.75
11roboflow / supervision
We write your reusable computer vision tools. 💜
+93 stars
from 51,361 · score 4.54
12xinntao / Real-ESRGAN
Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.
+92 stars
from 37,218 · score 4.53
13LMCache / LMCache
LMCache: Supercharge Your LLM with the Fastest KV Cache Layer
+92 stars
from 12,164 · score 4.53
14modelscope / FunASR
Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.
+88 stars
from 20,814 · score 4.49
15AUTOMATIC1111 / stable-diffusion-webui
Stable Diffusion web UI
+70 stars
from 165,144 · score 4.26
16kanaworksai-hue / audio-studio-mcp
Local AI BGM and sound effects for Claude Code and any MCP client. Stable Audio 3 on Apple Silicon (MLX) and Windows NVIDIA GPUs (PyTorch). No cloud, no API key.
+68 stars
from 491 · score 4.23
17deepinsight / insightface
State-of-the-art 2D and 3D Face Analysis Project
+58 stars
from 30,048 · score 4.08
18stas00 / ml-engineering
Machine Learning Engineering Open Book
+55 stars
from 19,589 · score 4.03
19ray-project / ray
Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
+52 stars
from 44,122 · score 3.97
20d2l-ai / d2l-en
Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 500 universities from 70 countries including Stanford, MIT, Harvard, and Cambridge.
+51 stars
from 29,931 · score 3.95
21TrenTorch / TrenTorch
Don't memorize ML. Understand it from first principles including Inference, Cuda, Deep Learning, Data Science and Reinforcement Learning
+51 stars
from 713 · score 3.95
22xingjian-bai / opal
OPAL: a reactive optimizer. A coding agent rewrites the optimizer while your model trains.
+51 stars
from 204 · score 3.95
23microsoft / JARVIS
JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf
+45 stars
from 25,498 · score 3.83
24NVIDIA / TensorRT-LLM
TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in a performant way.
+42 stars
from 14,945 · score 3.76
25huggingface / diffusers
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
+37 stars
from 34,807 · score 3.64
26labmlai / annotated_deep_learning_paper_implementations
🧑🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠
+35 stars
from 67,600 · score 3.58
27coqui-ai / TTS
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
+34 stars
from 46,141 · score 3.56
28BlueRingsLabs / no-shortcuts
Free Course : Data, Machine Learning, Deep Learning and AI Engineering, the long way round: the math, the code, the systems and the security. 173 lessons, 166 runnable labs, no shortcuts. Free under CC BY-NC 4.0.
+34 stars
from 132 · score 3.56
29ultralytics / yolov5
Ultralytics YOLOv5 in PyTorch for object detection, instance segmentation, classification, training, and export.
+26 stars
from 58,221 · score 3.30
30QuentinFuxa / WhisperLiveKit
Real-time, local speech-to-text with streaming ASR, speaker diarization, translation, and OpenAI/Deepgram-compatible APIs.
+26 stars
from 11,174 · score 3.30
31nerfstudio-project / nerfstudio
A collaboration friendly studio for NeRFs
+24 stars
from 12,115 · score 3.22
32keras-team / keras
Deep Learning for humans
+23 stars
from 64,388 · score 3.18
33mlfoundations / open_clip
An open source implementation of CLIP.
+23 stars
from 14,216 · score 3.18
34JaidedAI / EasyOCR
Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.
+22 stars
from 30,102 · score 3.14
35DLR-RM / stable-baselines3
PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
+22 stars
from 13,934 · score 3.14
36vwxyzjn / cleanrl
High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)
+20 stars
from 10,606 · score 3.04
37arc53 / DocsGPT
Private AI platform for agents, assistants and enterprise search. Built-in Agent Builder, Deep research, Document analysis, Multi-model support, and API connectivity for agents.
+19 stars
from 18,333 · score 3.00
38huggingface / pytorch-image-models
The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more
+18 stars
from 37,245 · score 2.94
39onnx / onnx
Open standard for machine learning interoperability
+17 stars
from 21,617 · score 2.89
40Jack-Cherish / PythonPark
Python 开源项目之「自学编程之路」，保姆级教程：AI实验室、宝藏视频、数据结构、学习指南、机器学习实战、深度学习实战、网络爬虫、大厂面经、程序人生、资源分享。
+17 stars
from 11,878 · score 2.89
41milesial / Pytorch-UNet
PyTorch implementation of the U-Net for image semantic segmentation with high quality images
+17 stars
from 11,724 · score 2.89
42microsoft / LoRA
Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"
+16 stars
from 13,877 · score 2.83
43huggingface / datasets
🤗 The largest hub of ready-to-use datasets for AI models with fast, easy-to-use and efficient data manipulation tools
+15 stars
from 22,087 · score 2.77
44bigscience-workshop / petals
🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading
+15 stars
from 10,664 · score 2.77
45huggingface / peft
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
+14 stars
from 21,851 · score 2.71
46speechbrain / speechbrain
A PyTorch-based Speech Toolkit
+13 stars
from 11,903 · score 2.64
47CorentinJ / Real-Time-Voice-Cloning
Clone a voice in 5 seconds to generate arbitrary speech in real-time
+12 stars
from 60,211 · score 2.56
48autogluon / autogluon
Fast and Accurate ML in 3 Lines of Code
+12 stars
from 10,795 · score 2.56
49Project-MONAI / MONAI
AI Toolkit for Healthcare Imaging
+12 stars
from 8,803 · score 2.56
50open-mmlab / mmdetection
OpenMMLab Detection Toolbox and Benchmark
+11 stars
from 33,009 · score 2.48
51ludwig-ai / ludwig
Low-code framework for building custom LLMs, neural networks, and other AI models
+11 stars
from 11,781 · score 2.48
52qubvel-org / segmentation_models.pytorch
Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.
+11 stars
from 11,780 · score 2.48
53RUCAIBox / RecBole
A unified, comprehensive and efficient recommendation library
+11 stars
from 4,596 · score 2.48
54sunlabuiuc / PyHealth
A deep learning toolkit for healthcare AI: EHR (MIMIC, eICU, OMOP), clinical text, signals and imaging. 30+ models, reproducible pipelines.
+11 stars
from 1,681 · score 2.48
55WZMIAOMIAO / deep-learning-for-image-processing
deep learning for image processing including classification and object-detection etc.
+9 stars
from 26,429 · score 2.30
56Megvii-BaseDetection / YOLOX
YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/
+9 stars
from 10,675 · score 2.30
57deepspeedai / DeepSpeed
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
+8 stars
from 43,273 · score 2.20
58PennyLaneAI / pennylane
PennyLane is an open-source quantum software platform for quantum computing, quantum machine learning, and quantum chemistry. Create meaningful quantum algorithms, from inspiration to implementation.
+8 stars
from 3,509 · score 2.20
59sczhou / CodeFormer
[NeurIPS 2022] Towards Robust Blind Face Restoration with Codebook Lookup Transformer
+7 stars
from 18,195 · score 2.08
60kyegomez / OpenMythos
A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.
+7 stars
from 14,907 · score 2.08
61ultralytics / yolov3
PyTorch implementation of YOLOv3, YOLOv3-SPP, and YOLOv3-tiny for real-time object detection with training, validation, inference, and multi-format export.
+7 stars
from 10,624 · score 2.08
62open-mmlab / mmdetection3d
OpenMMLab's next-generation platform for general 3D object detection.
+7 stars
from 6,562 · score 2.08
63Nixtla / neuralforecast
Scalable and user friendly neural :brain: forecasting algorithms.
+7 stars
from 4,295 · score 2.08
64yunjey / pytorch-tutorial
PyTorch Tutorial for Deep Learning Researchers
+6 stars
from 32,515 · score 1.95
65BlinkDL / RWKV-LM
RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding.
+6 stars
from 14,762 · score 1.95
66thu-ml / tianshou
An elegant PyTorch deep reinforcement learning library.
+6 stars
from 11,042 · score 1.95
67open-mmlab / OpenPCDet
OpenPCDet Toolbox for LiDAR-based 3D Object Detection.
+6 stars
from 5,748 · score 1.95
68Lightning-AI / pytorch-lightning
Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.
+5 stars
from 31,432 · score 1.79
69zenml-io / zenml
ZenML 🙏: One AI Platform from Pipelines to Agents. https://zenml.io.
+5 stars
from 5,628 · score 1.79
70pytorch / ignite
High-level library to help with training and evaluating neural networks in PyTorch flexibly and transparently.
+5 stars
from 4,794 · score 1.79
71jankrepl / deepdow
Portfolio optimization with deep learning.
+5 stars
from 1,194 · score 1.79
72lightly-ai / lightly
A python library for self-supervised learning and latent world models on images.
+4 stars
from 3,822 · score 1.61
73junyanz / pytorch-CycleGAN-and-pix2pix
Image-to-Image Translation in PyTorch
+3 stars
from 25,265 · score 1.39
74jacobgil / pytorch-grad-cam
Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.
+3 stars
from 13,000 · score 1.39
75aqlaboratory / openfold
Trainable, memory-efficient, and GPU-friendly PyTorch reproduction of AlphaFold 2
+3 stars
from 3,442 · score 1.39
76benedekrozemberczki / pytorch_geometric_temporal
PyTorch Geometric Temporal: Spatiotemporal Signal Processing with Neural Machine Learning Models (CIKM 2021)
+3 stars
from 2,993 · score 1.39
77takuseno / d3rlpy
An offline deep reinforcement learning library
+3 stars
from 1,685 · score 1.39
78KinWaiCheuk / nnAudio
Audio processing by using pytorch 1D convolution network
+3 stars
from 1,129 · score 1.39
79Mariewelt / OpenChem
OpenChem: Deep Learning toolkit for Computational Chemistry and Drug Design Research
+3 stars
from 756 · score 1.39
80wandb / wandb
The AI developer platform. Use Weights & Biases to train and fine-tune models, and manage models from experimentation to production.
+2 stars
from 11,309 · score 1.10
81dbolya / yolact
A simple, fully convolutional model for real-time instance segmentation.
+2 stars
from 5,250 · score 1.10
82deepchecks / deepchecks
Deepchecks: Tests for Continuous Validation of ML Models & Data. Deepchecks is a holistic open-source solution for all of your AI & ML validation needs, enabling to thoroughly test your data and models from research to production.
+2 stars
from 4,067 · score 1.10
83V2AI / Det3D
World's first general purpose 3D object detection codebse.
+2 stars
from 1,562 · score 1.10
84google-research / big_transferArchived
Official repository for the "Big Transfer (BiT): General Visual Representation Learning" paper.
+2 stars
from 1,541 · score 1.10
85keras-team / keras-hub
Pretrained model hub for Keras 3.
+2 stars
from 995 · score 1.10
86babysor / MockingBird
🚀Clone a voice in 5 seconds to generate arbitrary speech in real-time
+1 stars
from 36,881 · score 0.69
87allenai / allennlpArchived
An open-source NLP research library, built on PyTorch.
+1 stars
from 11,882 · score 0.69
88intel / ipex-llmArchived
Accelerate local LLM inference and finetuning (LLaMA, Mistral, ChatGLM, Qwen, DeepSeek, Mixtral, Gemma, Phi, MiniCPM, Qwen-VL, MiniCPM-V, etc.) on Intel XPU (e.g., local PC with iGPU and NPU, discrete GPU such as Arc, Flex and Max); seamlessly integrate with llama.cpp, Ollama, HuggingFace, LangChain, LlamaIndex, vLLM, DeepSpeed, Axolotl, etc.
+1 stars
from 8,844 · score 0.69
89stanfordnlp / stanza
Stanford NLP Python library for tokenization, sentence segmentation, NER, and parsing of many human languages
+1 stars
from 7,904 · score 0.69
90microsoft / MMdnn
MMdnn is a set of tools to help users inter-operate among different deep learning frameworks. E.g. model conversion and visualization. Convert models between Caffe, Keras, MXNet, Tensorflow, CNTK, PyTorch Onnx and CoreML.
+1 stars
from 5,803 · score 0.69
91superduper-io / superduper
Superduper: End-to-end framework for building custom AI applications and agents.
+1 stars
from 5,327 · score 0.69
92cornellius-gp / gpytorch
A highly efficient implementation of Gaussian Processes in PyTorch
+1 stars
from 3,930 · score 0.69
93jmschrei / pomegranate
Fast, flexible and easy to use probabilistic modelling in Python.
+1 stars
from 3,546 · score 0.69
94linto-ai / whisper-timestamped
Multilingual Automatic Speech Recognition with word-level timestamps and confidence
+1 stars
from 2,856 · score 0.69
95automl / Auto-PyTorch
Automatic architecture search and hyperparameter optimization for PyTorch
+1 stars
from 2,541 · score 0.69
96open-mmlab / mmengine
OpenMMLab Foundational Library for Training Deep Learning Models
+1 stars
from 1,505 · score 0.69
97allegro / allRank
allRank is a framework for training learning-to-rank neural models based on PyTorch.
+1 stars
from 1,012 · score 0.69
98agrimgupta92 / sgan
Code for "Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks", Gupta et al, CVPR 2018
+1 stars
from 919 · score 0.69
99gmalivenko / pytorch2keras
PyTorch to Keras model convertor
+1 stars
from 860 · score 0.69
100xiaoyufenfei / LEDNet
LEDNet: A Lightweight Encoder-Decoder Network for Real-time Semantic Segmentation
+1 stars
from 523 · score 0.69