Open-source deep-learning framework for building, training, and fine-tuning deep learning models using state-of-the-art Physics-ML methods

Solve puzzles. Improve your pytorch.

(N=1,2,3)-dimensional unfold (im2col) and fold (col2im) in PyTorch

Hunter is a flexible code tracing toolkit.

Never use print for debugging again

The implementation of "Self-Supervised Generalisation with Meta Auxiliary Learning" [NeurIPS 2019].

Official implementation of Auxiliary Learning by Implicit Differentiation [ICLR 2021]

FAIR Chemistry's library of machine learning methods for chemistry

Python dictionaries with advanced dot notation access

Matbench: Benchmarks for materials science property prediction

Using graph network to solve PDEs

[ICLR2025 Spotlight] Official implementation of Conflict-Free Inverse Gradients Method

Learning in infinite dimension with neural operators.

A Collection of Variational Autoencoders (VAE) in PyTorch.

A simple tutorial of Variational AutoEncoders with Pytorch

Pytorch implementation of Diffusion Models (https://arxiv.org/pdf/2006.11239.pdf)

Implementation of Denoising Diffusion Probabilistic Model in Pytorch

95.47% on CIFAR10 with PyTorch

PyTorch implementation of the U-Net for image semantic segmentation with high quality images

matrix multiplication in CUDA

Samples for CUDA Developers which demonstrates features in CUDA Toolkit

Source code examples from the Parallel Forall Blog

Flash Attention in ~100 lines of CUDA (forward pass only)

LLM training in simple, raw C/CUDA

Development repository for the Triton language and compiler

The simplest, fastest repository for training/finetuning medium-sized GPTs.