GitHub Trending Rank Radar

GitHub 开源项目趋势榜单 · 每日双快照 · 十一种榜单 · 日 / 月 / 年历史回看

GitHub

独立采集 · 开源数据

独立追踪 GitHub 星标的每一次脉动

每日两次快照,用差值还原真实增长——不是又一份热榜镜像。

浏览今日榜单 →
Star 范围 – k

2026-11-16 · #pytorch · 80 个仓库 · 按 star 排序repos · by stars

1
Python★ 168,994⑂ 35,210👁 1,283● 19,880⑃ 30,063▤ 284
🤗 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.
★ 168,994
2
Python★ 165,318⑂ 31,126👁 1,239● 7,928⑃ 3,374▤ 27
Stable Diffusion web UI
★ 165,318
3
Python★ 147,006⑂ 17,535👁 843● 9,755⑃ 6,316▤ 166
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.
★ 147,006
4
Jupyter Notebook★ 108,453⑂ 16,780👁 869● 253⑃ 626▤ 0
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
★ 108,453
5
Python★ 96,966⑂ 24,859👁 604● 19,883⑃ 47,020▤ 109
A high-throughput and memory-efficient inference and serving engine for LLMs
★ 96,966
6
Python★ 67,750⑂ 6,789👁 496● 145⑃ 155▤ 0
🧑‍🏫 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, ... 🧠
★ 67,750
7
Python★ 64,424⑂ 19,816👁 1,848● 13,086⑃ 10,265▤ 93
Deep Learning for humans
★ 64,424
8
Python★ 63,456⑂ 12,012👁 265● 13,003⑃ 8,414▤ 540
Ultralytics YOLO27, YOLO26, YOLO11, YOLOv8 — object detection, instance segmentation, semantic segmentation, image classification, pose estimation, object tracking
★ 63,456
9
Python★ 60,242⑂ 9,382👁 925● 1,124⑃ 155▤ 0
Clone a voice in 5 seconds to generate arbitrary speech in real-time
★ 60,242
10
Python★ 58,272⑂ 17,434👁 379● 9,428⑃ 3,071▤ 10
Ultralytics YOLOv5 in PyTorch for object detection, instance segmentation, classification, training, and export.
★ 58,272
11
Python★ 51,633⑂ 4,958👁 289● 595⑃ 2,092▤ 57
We write your reusable computer vision tools. 💜
★ 51,633
12
Jupyter Notebook★ 50,022⑂ 7,817👁 1,261● 77⑃ 202▤ 1
Learn how to develop, deploy and iterate on production-grade ML applications.
★ 50,022
13
Python★ 46,229⑂ 6,163👁 334● 1,243⑃ 799▤ 98
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
★ 46,229
14
Python★ 44,291⑂ 8,285👁 481● 23,323⑃ 44,385▤ 134
Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
★ 44,291
15
Python★ 43,326⑂ 5,072👁 350● 3,518⑃ 4,614▤ 120
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
★ 43,326
16
Python★ 42,520⑂ 4,861👁 164● 341⑃ 117▤ 14
VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning
★ 42,520
17
Python★ 37,704⑂ 6,279👁 510● 511⑃ 65▤ 8
GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.
★ 37,704
18
Python★ 37,508⑂ 4,537👁 257● 769⑃ 131▤ 10
Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.
★ 37,508
19
Python★ 37,284⑂ 5,230👁 314● 1,052⑃ 905▤ 81
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
★ 37,284
20
Python★ 36,865⑂ 5,148👁 298● 889⑃ 102▤ 1
🚀Clone a voice in 5 seconds to generate arbitrary speech in real-time
★ 36,865
21
Python★ 35,583⑂ 3,192👁 123● 221⑃ 1,210▤ 67
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.
★ 35,583
22
Python★ 34,917⑂ 7,480👁 219● 5,751⑃ 8,491▤ 97
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
★ 34,917
23
Python★ 30,228⑂ 6,134👁 518● 2,627⑃ 226▤ 2
State-of-the-art 2D and 3D Face Analysis Project
★ 30,228
24
Python★ 30,141⑂ 3,623👁 327● 1,087⑃ 289▤ 23
Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.
★ 30,141
25
C++★ 24,052⑂ 4,551👁 566● 3,916⑃ 3,195▤ 50
ncnn is a high-performance neural network inference framework optimized for the mobile platform
★ 24,052
26
★ 23,869⑂ 3,145👁 439● 71⑃ 370▤ 208
🏆 A ranked list of awesome machine learning Python libraries. Updated weekly.
★ 23,869
27
Python★ 23,286⑂ 2,568👁 7● 523⑃ 67▤ 58
Image inpainting tool powered by SOTA AI Model. Remove any unwanted object, defect, people from your pictures or erase and replace(powered by stable diffusion) any thing on your pictures.
★ 23,286
28
C++★ 22,317⑂ 4,449👁 264● 8,895⑃ 21,801▤ 92
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
★ 22,317
29
Python★ 21,033⑂ 2,129👁 113● 1,809⑃ 2,001▤ 87
Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.
★ 21,033
30
Python★ 19,717⑂ 1,303👁 156● 44⑃ 98▤ 0
Machine Learning Engineering Open Book
★ 19,717
31
Jupyter Notebook★ 19,529⑂ 5,388👁 378● 152⑃ 40▤ 0
本项目将《动手学深度学习》(Dive into Deep Learning)原书中的MXNet实现改为PyTorch实现。
★ 19,529
32
Jupyter Notebook★ 19,418⑂ 5,244👁 155● 253⑃ 203▤ 0
Materials for the Learn PyTorch for Deep Learning: Zero to Mastery course.
★ 19,418
33
Jupyter Notebook★ 18,594⑂ 2,758👁 195● 452⑃ 613▤ 4
Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama model family and using them on various provider services
★ 18,594
34
Python★ 18,375⑂ 2,254👁 96● 701⑃ 2,561▤ 28
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.
★ 18,375
35
Python★ 18,234⑂ 3,720👁 314● 379⑃ 52▤ 1
[NeurIPS 2022] Towards Robust Blind Face Restoration with Codebook Lookup Transformer
★ 18,234
36
Jupyter Notebook★ 17,889⑂ 3,877👁 309● 18⑃ 2▤ 0
深度学习入门教程, 优秀文章, Deep Learning Tutorial
★ 17,889
37
★ 16,758⑂ 2,837👁 546● 21⑃ 156▤ 0
A comprehensive list of pytorch related content on github,such as different models,implementations,helper libraries,tutorials etc.
★ 16,758
38
Python★ 16,621⑂ 1,301👁 85● 299⑃ 79▤ 7
pix2tex: Using a ViT to convert images of equations into LaTeX code.
★ 16,621
39
Python★ 16,439⑂ 2,863👁 86● 112⑃ 182▤ 0
Nano vLLM
★ 16,439
40
Rust★ 16,280⑂ 1,128👁 92● 1,646⑃ 4,624▤ 46
Burn is a next generation tensor library and Deep Learning Framework that doesn't compromise on flexibility, efficiency and portability.
★ 16,280
41
★ 15,966⑂ 2,716👁 363● 3,787⑃ 3,813▤ 94
The Cloud Native AI Platform
★ 15,966
42
Jupyter Notebook★ 15,881⑂ 2,602👁 196● 362⑃ 147▤ 4
stable diffusion webui colab
★ 15,881
43
Python★ 15,692⑂ 2,081👁 288● 258⑃ 38▤ 1
Bringing Old Photo Back to Life (CVPR 2020 oral)
★ 15,692
44
Python★ 15,079⑂ 2,936👁 119● 4,252⑃ 17,811▤ 96
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.
★ 15,079
45
Jupyter Notebook★ 14,930⑂ 3,918👁 278● 55⑃ 34▤ 0
Natural Language Processing Tutorial for Deep Learning Researchers
★ 14,930
46
Python★ 14,366⑂ 1,850👁 8● 2,078⑃ 3,492▤ 40
An open source AutoML toolkit for automate machine learning lifecycle, including feature engineering, neural architecture search, model compression and hyper-parameter tuning.
★ 14,366
47
Python★ 14,015⑂ 2,183👁 68● 1,605⑃ 666▤ 33
PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
★ 14,015
48
C++★ 12,356⑂ 2,274👁 238● 379⑃ 91▤ 0
超轻量级中文ocr,支持竖排文字识别, 支持ncnn、mnn、tnn推理 ( dbnet(1.8M) + crnn(2.5M) + anglenet(378KB)) 总模型仅4.7M
★ 12,356
49
Python★ 9,991⑂ 2,862👁 48● 2,450⑃ 1,345▤ 45
OpenMMLab Semantic Segmentation Toolbox and Benchmark.
★ 9,991
50
Python★ 9,837⑂ 807👁 96● 309⑃ 273▤ 4
SANA & Sol: Efficient Generative Models and Full-Stack Training & Inference Engines for Image, Video, and World Modeling
★ 9,837
当月每日飙升 Top10 摘要

年度月度榜入口