Metadata-Version: 2.4
Name: nvMolKit
Version: 0.5.0
Summary: CUDA-backed python library for accelerating common RDKit molecular operations
Author-email: NVIDIA BioNeMo <bionemofeedback@nvidia.com>
License-Expression: Apache-2.0
Project-URL: Homepage, https://nvidia-digital-bio.github.io/nvMolKit/
Project-URL: Documentation, https://nvidia-digital-bio.github.io/nvMolKit/
Project-URL: Repository, https://github.com/NVIDIA-Digital-Bio/nvMolKit
Project-URL: Issues, https://github.com/NVIDIA-Digital-Bio/nvMolKit/issues
Project-URL: Changelog, https://github.com/NVIDIA-Digital-Bio/nvMolKit/releases
Keywords: cheminformatics,rdkit,cuda,gpu,molecules,pytorch
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Science/Research
Classifier: Operating System :: POSIX :: Linux
Classifier: Environment :: GPU :: NVIDIA CUDA :: 12
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Programming Language :: Python :: 3.14
Classifier: Programming Language :: C++
Classifier: Topic :: Scientific/Engineering :: Chemistry
Requires-Python: <3.15,>=3.10
Description-Content-Type: text/markdown
Requires-Dist: numpy>=1.23
Requires-Dist: torch>=2.1
Requires-Dist: triton
Requires-Dist: rdkit==2026.3.1
Requires-Dist: nvidia-cuda-runtime-cu12>=12.0
Provides-Extra: test
Requires-Dist: pandas; extra == "test"
Requires-Dist: psutil; extra == "test"
Requires-Dist: pytest; extra == "test"
Requires-Dist: ruff; extra == "test"
Provides-Extra: docs
Requires-Dist: sphinx; extra == "docs"
Requires-Dist: nvidia-sphinx-theme; extra == "docs"
Requires-Dist: autodocsumm; extra == "docs"
Requires-Dist: myst-parser; extra == "docs"
Requires-Dist: jupyter-sphinx; extra == "docs"
Provides-Extra: autotune
Requires-Dist: optuna; extra == "autotune"

nvMolKit is a CUDA-backed Python library that accelerates common
[RDKit](https://www.rdkit.org/) molecular operations. It links against RDKit and
operates on standard RDKit molecular representations.

nvMolKit mirrors RDKit's APIs but exposes batch-oriented
variants so many molecules can be processed in parallel on the GPU. Operations
that do not modify structures return asynchronous GPU results that can be
converted to PyTorch tensors or NumPy arrays; APIs that modify molecules apply
changes in place, consistent with RDKit.

An NVIDIA GPU with compute capability 7.0 (Volta) or newer and a Linux
environment with CUDA 12 are required. For installation options, API reference, and
examples, see the
[project documentation](https://nvidia-digital-bio.github.io/nvMolKit/).
