Discover trending repositories tagged pytorch, ranked by recent growth and activity.
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
GitHub repository with 115,704 stars and 13,538 forks.
Trending score: 3.83; stars gained: +129; forks gained: +22.
Language: Python
Topics: ai, comfy, comfyui, python, pytorch, stable-diffusion
π€ 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.
GitHub repository with 161,277 stars and 33,411 forks.
Trending score: 2.96; stars gained: +38; forks gained: +8.
Language: Python
Topics: audio, deep-learning, deepseek, gemma, glm, hacktoberfest
VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning
GitHub repository with 24,487 stars and 2,821 forks.
Trending score: 2.78; stars gained: +680; forks gained: +69.
Language: Python
Topics: audio, deeplearning, minicpm, python, pytorch, speech
A high-throughput and memory-efficient inference and serving engine for LLMs
GitHub repository with 81,936 stars and 17,651 forks.
Trending score: 2.08; stars gained: +131; forks gained: +40.
Language: Python
Topics: amd, blackwell, cuda, deepseek, deepseek-v3, gpt
Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
GitHub repository with 42,769 stars and 7,634 forks.
Trending score: 2.03; stars gained: +10; forks gained: -2.
Language: Python
Topics: data-science, deep-learning, deployment, distributed, hyperparameter-optimization, hyperparameter-search
Industrial-grade speech recognition toolkit: 170x realtime, 50+ languages, speaker diarization, emotion detection, streaming, and OpenAI-compatible API.
GitHub repository with 16,750 stars and 1,720 forks.
Trending score: 1.93; stars gained: +56; forks gained: +2.
Language: Python
Topics: pytorch, speech-recognition, paraformer, punctuation, speaker-diarization, voice-activity-detection
Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search, and conversational systems.
GitHub repository with 25,459 stars and 2,830 forks.
Trending score: 1.80; stars gained: +5; forks gained: +4.
Language: MDX
Topics: agent, agents, ai, gemini, generative-ai, gpt-4
A framework for efficient model inference with omni-modality models
GitHub repository with 4,937 stars and 1,048 forks.
Trending score: 1.37; stars gained: +26; forks gained: +2.
Language: Python
Topics: audio-generation, diffusion, image-generation, inference, model-serving, multimodal
We write your reusable computer vision tools. π
GitHub repository with 39,978 stars and 3,605 forks.
Trending score: 1.33; stars gained: +13; forks gained: +0.
Language: Python
Topics: classification, coco, computer-vision, deep-learning, hacktoberfest, image-processing
Stable Diffusion web UI
GitHub repository with 163,383 stars and 30,374 forks.
Trending score: 1.28; stars gained: +10; forks gained: +3.
Language: Python
Topics: deep-learning, diffusion, image-generation, image2image, img2img, text2image
Estimate whether a Hugging Face model fits and fine-tunes on your local GPU.
GitHub repository with 313 stars and 43 forks.
Trending score: 1.28; stars gained: +23; forks gained: +5.
Language: Python
Topics: bitsandbytes, fine-tuning, gpu, hugging-face, llm, lora
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
GitHub repository with 42,462 stars and 4,849 forks.
Trending score: 1.25; stars gained: +19; forks gained: +0.
Language: Python
Topics: billion-parameters, compression, data-parallelism, deep-learning, gpu, inference
Official Implementation of LongLive-RAG: A general retrieval-augmented framework for long video generation.
GitHub repository with 41 stars and 0 forks.
Trending score: 1.18; stars gained: +14; forks gained: +0.
Language: Python
Topics: autoregressive, diffusion-models, generative-ai, long-video-generation, pytorch, retrieval-augmented-generation
Building a small LLM in PyTorch from scratch - a step-by-step journey through Stanford CS336.
GitHub repository with 58 stars and 2 forks.
Trending score: 1.16; stars gained: +15; forks gained: +0.
Language: Python
Topics: cs336, llm, pytorch
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
GitHub repository with 20,723 stars and 3,959 forks.
Trending score: 1.07; stars gained: +12; forks gained: +1.
Language: C++
Topics: ai-framework, deep-learning, hardware-acceleration, machine-learning, neural-networks, onnx
Fast and Accurate ML in 3 Lines of Code
GitHub repository with 10,447 stars and 1,158 forks.
Trending score: 1.01; stars gained: +10; forks gained: +2.
Language: Python
Topics: autogluon, automated-machine-learning, automl, computer-vision, data-science, deep-learning
Visualizer for neural network, deep learning and machine learning models
GitHub repository with 33,031 stars and 3,125 forks.
Trending score: 0.97; stars gained: +9; forks gained: +0.
Language: JavaScript
Topics: ai, coreml, deep-learning, deeplearning, keras, machine-learning
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.
GitHub repository with 13,801 stars and 2,436 forks.
Trending score: 0.93; stars gained: +8; forks gained: +7.
Language: Python
Topics: blackwell, cuda, llm-serving, moe, pytorch
Accessible large language models via k-bit quantization for PyTorch.
GitHub repository with 8,255 stars and 859 forks.
Trending score: 0.88; stars gained: +7; forks gained: +1.
Language: Python
Topics: llm, machine-learning, pytorch, qlora, quantization
Bilingual (δΈζ+EN) ML / LLM / diffusion / agent interview cheat sheets for AI η§ζ β auto-generated by the ARIS /render-html workflow into single-file HTML, reads anywhere β plus a CVβDBLP-fact-checked academic homepage generator and long-form blogs/surveys π±
GitHub repository with 161 stars and 6 forks.
Trending score: 0.88; stars gained: +7; forks gained: +0.
Language: Python
Topics: ai-interview, aris, autumn-recruiting, cheatsheet, chinese, claude-code
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
GitHub repository with 36,846 stars and 5,162 forks.
Trending score: 0.86; stars gained: +3; forks gained: +0.
Language: Python
Topics: pytorch, resnet, pretrained-models, pretrained-weights, distributed-training, mobile-deep-learning
ViGeo: Towards Consistent Video Geometry Estimation
GitHub repository with 68 stars and 1 forks.
Trending score: 0.84; stars gained: +6; forks gained: +0.
Language: Python
Topics: depth-estimation, feed-forward-models, foundation-models, pytorch
A retargetable MLIR-based machine learning compiler and runtime toolkit.
GitHub repository with 3,787 stars and 918 forks.
Trending score: 0.74; stars gained: +3; forks gained: +0.
Language: C++
Topics: mlir, vulkan, tensorflow, spirv, cuda, jax
π€ Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
GitHub repository with 33,771 stars and 7,021 forks.
Trending score: 0.74; stars gained: +4; forks gained: +0.
Language: Python
Topics: deep-learning, diffusion, image-generation, pytorch, score-based-generative-modeling, image2image