An unofficial implementation of both ViT-VQGAN and RQ-VAE in Pytorch

Implementation of Imagen, Google's Text-to-Image Neural Network, in Pytorch

TorchMultimodal is a PyTorch library for training state-of-the-art multimodal multi-task models at scale.

Prevent PyTorch's `CUDA error: out of memory` in just 1 line of code.

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

Compiler for Neural Network hardware accelerators

A C++ standalone library for machine learning

Tensors and neural networks in Haskell

OCaml bindings for PyTorch

yolort is a runtime stack for yolov5 on specialized accelerators such as tensorrt, libtorch, onnxruntime, tvm and ncnn.

CakeML: A Verified Implementation of ML

Research programming language for concurrent ownership

The Vellvm (Verified LLVM) coq development.