Stars
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…
A Datacenter Scale Distributed Inference Serving Framework
A list of paper templates in the area of machine learning.
Ecosystem of libraries and tools for writing and executing fast GPU code fully in Rust.
NVIDIA Math Libraries for the Python Ecosystem
Implementation for ICLR2024 Oral paper "Unified Generative Modeling of 3D Molecules with Bayesian Flow Networks"
E3x is a JAX library for constructing efficient E(3)-equivariant deep learning architectures built on top of Flax.
A collection of QM data for training potential functions
Moleculib is a python library for preparing and processing biomolecular data in machine learning pipelines.
[ARCHIVED] The C++ parallel algorithms library. See https://github.com/NVIDIA/cccl
Tools for building equivariant polynomials on reductive Lie groups.
A machine learning compiler for GPUs, CPUs, and ML accelerators
Variational autoencoders on categorical and continuous data using jax
Materials science with Python at the atomic-scale
Permutation Equivariant Lorentz Invariant/Covariant Aggregator Network
Differentiable, Hardware Accelerated, Molecular Dynamics
The LLVM Project is a collection of modular and reusable compiler and toolchain technologies.
MACE - Fast and accurate machine learning interatomic potentials with higher order equivariant message passing.
Elegant easy-to-use neural networks + scientific computing in JAX. https://docs.kidger.site/equinox/
Equivariant GNN for the prediction of atomic multipoles up to quadrupoles.