Metadata-Version: 2.4
Name: rapidsmpf-cu13
Version: 26.4.0
Summary: Multi-GPU and distributed-memory algorithms
Author: NVIDIA Corporation
License-Expression: Apache-2.0
Classifier: Intended Audience :: Developers
Classifier: Topic :: Database
Classifier: Topic :: Scientific/Engineering
Classifier: Programming Language :: Python
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Programming Language :: Python :: 3.14
Project-URL: Homepage, https://github.com/rapidsai/rapidsmpf
Requires-Python: >=3.11
Requires-Dist: cuda-python<14.0,>=13.0.1
Requires-Dist: cupy-cuda13x>=13.6.0
Requires-Dist: librapidsmpf-cu13==26.4.*
Requires-Dist: numpy<3.0,>=1.23
Requires-Dist: pylibcudf-cu13==26.4.*
Requires-Dist: rmm-cu13==26.4.*
Requires-Dist: ucxx-cu13==0.49.*
Provides-Extra: test
Requires-Dist: cudf-cu13==26.4.*; extra == "test"
Requires-Dist: dask-cuda==26.4.*; extra == "test"
Requires-Dist: dask-cudf-cu13==26.4.*; extra == "test"
Requires-Dist: nvidia-ml-py>=12; extra == "test"
Requires-Dist: psutil; extra == "test"
Requires-Dist: pytest; extra == "test"
Description-Content-Type: text/markdown

# RapidsMPF

Collection of multi-GPU, distributed memory algorithms. RapidsMPF provides a unified
framework for asynchronous, multi-GPU pipelines using simple streaming primitives built
on RAPIDS components.

## Documentation

- [Getting Started](https://docs.rapids.ai/api/rapidsmpf/nightly/getting-started/)
- [Background](https://docs.rapids.ai/api/rapidsmpf/nightly/background/)
- [Configuration Options](https://docs.rapids.ai/api/rapidsmpf/nightly/configuration/)
- [Python API Reference](https://docs.rapids.ai/api/rapidsmpf/nightly/python/api/)
- [C++ API Reference](https://docs.rapids.ai/api/librapidsmpf/nightly/)
- [Glossary](https://docs.rapids.ai/api/rapidsmpf/nightly/glossary/)

## Build from Source

```bash
git clone https://github.com/rapidsai/rapidsmpf.git
cd rapidsmpf
mamba env create --name rapidsmpf-dev --file conda/environments/all_cuda-131_arch-$(uname -m).yaml
./build.sh
```

See the [Getting Started guide](https://docs.rapids.ai/api/rapidsmpf/nightly/getting-started/)
for debug builds, AddressSanitizer, MPI/UCX test suites, and rrun launcher details.
