MESS: Modern Electronic Structure Simulations

Force-field-enhanced Neural Networks optimized library

Tile primitives for speedy kernels

Shows some minimal examples of how to call JAX (HLO/AOT-compiled) from C++.

Tools for building equivariant polynomials on reductive Lie groups.

A curated list of resources for learning and exploring Triton, OpenAI's programming language for writing efficient GPU code.

cuEquivariance is a math library that is a collective of low-level primitives and tensor ops to accelerate widely-used models, like DiffDock, MACE, Allegro and NEQUIP, based on equivariant neural n…

CUDA implementations of MACE models

Everything you want to know about Google Cloud TPU

High level API for using machine learning models in OpenMM simulations

A batteries-included toolkit for the GPU-accelerated OpenMM molecular simulation engine.

Jax implementation for the paper "Sampling-based inference for large linear models, with application to linearised Laplace"

CSuite: A Suite of Benchmark Datasets for Causality

Pytorch code for "Improving Self-Supervised Learning by Characterizing Idealized Representations"

Fast and Easy Infinite Neural Networks in Python

Benchmarks for the Synbols project. Synbols is a ServiceNow Research project that was started at Element AI.

JAX-based neural network library

Transfer Learning library for Deep Neural Networks.

A generic interface for linear algebra backends

Code for the paper "Bayesian Neural Network Priors Revisited"

Differentiable convex optimization layers

A Python-embedded modeling language for convex optimization problems.

Code for the Neural Processes website and replication of 4 papers on NPs. Pytorch implementation.

A Machine Learning workflow for Slurm.

PyTorch-SSO: Scalable Second-Order methods in PyTorch

Code for "Depth Uncertainty in Neural Networks" (https://arxiv.org/abs/2006.08437)

Fault-tolerant, highly scalable GPU orchestration, and a machine learning framework designed for training models with billions to trillions of parameters

Model interpretability and understanding for PyTorch

Deep Neural Decision Trees