Tensors and Dynamic neural networks in Python with strong GPU acceleration

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.

Fast and memory-efficient exact attention

A PyTorch-based Speech Toolkit

Hydra is a framework for elegantly configuring complex applications

PyTorch Lightning + Hydra. A very user-friendly template for ML experimentation. ⚡🔥⚡

Sacred is a tool to help you configure, organize, log and reproduce experiments developed at IDSIA.

Machine learning metrics for distributed, scalable PyTorch applications.

pytorch-kaldi is a project for developing state-of-the-art DNN/RNN hybrid speech recognition systems. The DNN part is managed by pytorch, while feature extraction, label computation, and decoding a���

Flexible Python configuration system. The last one you will ever need.

PyTorch Extension Library of Optimized Scatter Operations

KErnel OPerationS, on CPUs and GPUs, with autodiff and without memory overflows

H-Net: Hierarchical Network with Dynamic Chunking

Debug PyTorch code using PySnooper

Constrained optimization toolkit for PyTorch

Research workflows made easy, locally and in the Cloud.

Kernel Tuner

OSLO: Open Source framework for Large-scale model Optimization

Unofficial description of the CUDA assembly (SASS) instruction sets.

A high-performance library for compressed ndarrays, with a flexible computational engine