#pytorch

The nnsight package enables interpreting and manipulating the internals of deep learned models.

Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding

High-performance automatic differentiation of LLVM and MLIR.

Compatibility layer for common array libraries to support the Array API

High-performance safetensors model loader

Python SDK to interact with the Hopsworks API

Qualcomm® AI Hub Models is our collection of state-of-the-art machine learning models optimized for performance (latency, memory etc.) and ready to deploy on Qualcomm® devices.

High Performance Computation for N-D Tensors in .NET, identical API to NumPy.

A highly efficient implementation of Gaussian Processes in PyTorch

The fastai deep learning library

Support PyTorch model conversion with LiteRT.

Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.

A Python library for anomaly detection across tabular, time series, graph, text, image, and audio data. 60+ detectors, benchmark-backed ADEngine orchestration, and an agentic workflow for AI agents.

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

Tensor Fusion is a state-of-the-art GPU virtualization and pooling solution designed to optimize GPU cluster utilization to its fullest potential.

Open-source tabular foundation model for fast, training-free regression with predictive distributions.

Tools for handling multimodal data in machine learning projects.

Data manipulation and transformation for audio signal processing, powered by PyTorch

Open-source framework for uncertainty and deep learning models in PyTorch 🌱

End-to-end ML toolkit automating the complete workflow — data profiling, preprocessing, feature engineering, model selection, training, validation, explainability, drift monitoring, fairness checks, and interactive HTML reporting. Includes a full CLI for zero-code ML pipelines. Python 3.10+.

Flexible and powerful tensor operations for readable and reliable code (for pytorch, jax, TF and others)

Open3D: A Modern Library for 3D Data Processing

Deep universal probabilistic programming with Python and PyTorch

AI on the way. An auto deep learning pipe dream. An RDBMS approach to deep learning. Declarative, explainable, scalable, optimizable, easy to deploy, all that good stuff.

A Machine Learning Library for Vector Fonts

Multi-dimensional arrays (tensors) and numerical definitions for Elixir

PyTorch model profiler for computing MACs and parameter counts to measure deep learning model complexity.

S2FFT: Differentiable and accelerated spherical transforms

IREE's PyTorch Frontend, based on Torch Dynamo.

Visualizer for neural network, deep learning and machine learning models