nvidia-cusparse

CUSPARSE native runtime libraries

nvidia-cusparse License unclear Active v12.8.2.51 released 2026-06-29

Install

nvidia-cusparse on PyPI

pip

pip install nvidia-cusparse

uv

uv add nvidia-cusparse

poetry

poetry add nvidia-cusparse

Package facts

License	not declared (unclear)
Python support	supports the current Python release (>=3)
Install friction	medium — platform-specific wheel
Runtime dependencies	1 — nvidia-nvjitlink
Maintenance	actively maintained — 45 days since the last release
First released	2020-09-18
Popularity	one of the top 1,000 most-downloaded packages on PyPI (30-day window, as of 2026-08-13)
Known vulnerabilities	none known (OSV.dev, checked 2026-08-13)

Evidence: nvidia_cusparse-12.8.2.51-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl; nvidia_cusparse-12.8.2.51-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl; nvidia_cusparse-12.8.2.51-py3-none-win_amd64.whl

Keywords: cuda, nvidia, runtime, machine learning, deep learning

Development Status :: 4 - BetaIntended Audience :: DevelopersIntended Audience :: EducationIntended Audience :: Science/ResearchNatural Language :: EnglishOperating System :: Microsoft :: WindowsOperating System :: POSIX :: LinuxProgramming Language :: Python :: 3Programming Language :: Python :: 3 :: OnlyProgramming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.5Programming Language :: Python :: 3.6Programming Language :: Python :: 3.7Programming Language :: Python :: 3.8Programming Language :: Python :: 3.9Topic :: Scientific/EngineeringTopic :: Scientific/Engineering :: Artificial IntelligenceTopic :: Scientific/Engineering :: MathematicsTopic :: Software DevelopmentTopic :: Software Development :: Libraries

About nvidia-cusparse

from the package's own PyPI description — quoted content, verbatim

CUSPARSE native runtime libraries

Read as markdown · JSON record · Homepage

AI interpretation — verify before relying

AI-generated interpretation of the package facts above; every digit, version, license, or vulnerability id it cites is grounded in the facts already shown on this page

Provides NVIDIA CUSPARSE native runtime libraries for GPU-accelerated sparse matrix operations on CUDA-enabled hardware.

Medium install friction due to platform-specific wheels (Linux x86_64, Linux aarch64, Windows); requires nvidia-nvjitlink as a runtime dependency. Package is actively maintained with a release 45 days old.

License status is unclear—no SPDX identifier or raw license text is available in the package metadata, making it difficult to assess legal compatibility before use.

Usage

pip install nvidia-cusparse==12.8.2.51
import nvidia.cusparse

Requires NVIDIA CUDA-capable GPU and CUDA toolkit installed on the system; platform-specific wheels limit availability to Linux (x86_64, aarch64) and Windows.

Verdict: A specialized runtime library for NVIDIA CUDA sparse matrix operations, actively maintained and in the top 1000 PyPI packages. Medium install friction and unclear licensing are the main concerns; no known vulnerabilities. Suitable for GPU-accelerated scientific computing, but requires CUDA hardware and careful license review before production deployment.

Needs verification

Whether the unclear license status reflects proprietary NVIDIA licensing or a documentation gap in the package metadata.
Whether nvidia-nvjitlink dependency is automatically satisfied or requires separate installation steps.
Compatibility matrix details for specific CUDA versions and GPU architectures beyond the wheel platform tags.

cuda sparse matrix operationsnvidia cusparse gpusparse linear algebra cudanvidia gpu runtime librariescusparse native runtimegpu accelerated sparse tensorscuda sparse matrix library