A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch

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

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

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

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

A simple way to calibrate your neural network.

A batched offline inference oriented version of segment-anything

Official Implementation of "ADOPT: Modified Adam Can Converge with Any β2 with the Optimal Rate"

Differentiable ODE solvers with full GPU support and O(1)-memory backpropagation.

Finite Element Analysis Library in Python

Stratified Transformer for 3D Point Cloud Segmentation (CVPR 2022)

Erwin: A Tree-based Hierarchical Transformer for Large-scale Physical Systems [ICML'25]