Open Source PyTorch Projects
Discover 36 open source PyTorch repositories from GitHub, each with an analysis of what it does, key features, use cases and alternatives. PyTorch projects here are most often combined with Machine Learning, Deep Learning and Python. Last updated October 3, 2026.
36 repositories · updated October 3, 2026
notebooks: Learn and Apply Computer Vision Models
Roboflow notebooks is a hands-on tutorial collection for computer vision, covering model training, inference, detection, segmentation, and related tasks. Use it to explore techniques and run examples in hosted notebook environments.
Spark-TTS: Generate Speech and Clone Voices from Text
Spark-TTS is a PyTorch inference project for bilingual text-to-speech and zero-shot voice cloning. It uses a Qwen2.5-based model to generate speech and supports adjustable voice characteristics.
stable-diffusion-webui: Generate Images with Stable Diffusion
A Gradio-based web interface for generating and editing images with Stable Diffusion. It gives artists and other local users a browser-based workflow for prompts, image-to-image tools, model options, and extensions.
Spotlight: Deep Recommender Models with PyTorch
Spotlight is a Python library built on PyTorch for developing deep and shallow recommender models. It offers a comprehensive set of building blocks for various loss functions, representations, and utilities for handling recommendation datasets. This tool is designed for rapid exploration and prototyping of new recommender systems.
PETSA: Adapt Time-Series Forecasters at Test Time
PETSA is a parameter-efficient test-time adaptation method for time-series forecasting. It updates small input and output calibration modules rather than the full model, targeting non-stationary data with lower adaptation costs.
flash-attention: Compute Exact Attention Faster and with Less Memory
FlashAttention provides GPU-optimized implementations of exact attention for deep learning, reducing memory use while improving speed. It is aimed at practitioners training or serving Transformer models who can build and run GPU kernels.
gaussian-splatting: Reconstruct and Render 3D Scenes in Real Time
The authors’ reference implementation of 3D Gaussian Splatting, which reconstructs scenes from posed images and renders novel viewpoints. It suits graphics and vision researchers and practitioners with CUDA-capable GPUs who need a trainable, interactive scene representation.
aimet: Quantize and Compress Trained Neural Networks
AIMET helps ML engineers reduce the compute and memory needs of trained neural networks through quantization and compression. It supports PyTorch and ONNX workflows for preparing models for efficient deployment, including on edge devices.
PartCrafter: Generate Structured 3D Meshes from Images
PartCrafter generates part-separated 3D objects and scenes from a single RGB image using compositional latent diffusion. It suits researchers and developers exploring image-to-3D generation who have access to a CUDA-enabled GPU.
litgpt: Train, Fine-Tune, and Deploy Large Language Models
LitGPT provides implementations and workflows for pretraining, fine-tuning, evaluating, and serving a range of large language models. It suits developers and researchers who want configurable training recipes and direct control over model code.
HunyuanVideo-Avatar: Create Audio-Driven Character Videos
HunyuanVideo-Avatar generates dynamic, emotion-controllable videos of one or more characters from avatar images and audio. It is aimed at creators and researchers who need expressive talking-avatar or dialogue video generation and have access to compatible NVIDIA GPU hardware.
StreamDiffusion: Generate Images in Real Time with Diffusion
StreamDiffusion adapts diffusion pipelines for interactive image generation, with support for text-to-image and image-to-image workflows. It targets developers building responsive GPU-powered demos and applications.