Reusable DFT Grids for the Masses

A few utils for JAX (and general python) programming

train and use graph-based ML models of potential energy surfaces

Interactive browser visualizations for materials science: periodic tables, 3d crystal structures, MD trajectories, heatmaps, scatter plots, histograms.

Graph Neural Network Library for PyTorch

Zero Shot Molecular Generation via Similarity Kernels

Repository of Quantum Datasets Publicly Available

CUDA implementations of MACE models

Nonlinear optimisation (root-finding, least squares, ...) in JAX+Equinox. https://docs.kidger.site/optimistix/

MACE - Fast and accurate machine learning interatomic potentials with higher order equivariant message passing.

PySCF on IPU

one billion quantum mechanical simulations containing 9-11 heavy atoms

A library for unit scaling in PyTorch

Equivariant machine learning interatomic potentials in JAX.

Fast and Accurate Predictions from 3D Molecular Structures

TessellateIPU: low level Poplar tile programming from Python

Graphium: Scaling molecular GNNs to infinity.

IPU-specific extensions to PopTorch

JAX for Graphcore IPU (experimental)

PyTorch interface for the IPU

Example code and applications for machine learning on Graphcore IPUs

Graph algorithms for machine learning frameworks

A tech debt reading and resources list - to help diagnose, prevent and control tech debt.

Mirror of Apache Arrow site

Apache Arrow is the universal columnar format and multi-language toolbox for fast data interchange and in-memory analytics

Apache Arrow is a cross-language development platform for in-memory data. It specifies a standardized language-independent columnar memory format for flat and hierarchical data, organized for effic…