nvidia-cusparse
CUSPARSE native runtime libraries
Decision gist · record as of 2026-08-14
Yes, if you are building or using a CUDA-based application that requires sparse matrix operations and your system matches one of the supported platforms (Linux x86_64/aarch64 or Windows x86_64). The package is actively maintained and has no known vulnerabilities. Install only if you have NVIDIA GPU hardware and the CUDA toolkit already set up; this is a runtime library, not a standalone tool.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires NVIDIA GPU hardware and CUDA toolkit; platform-specific wheel (Linux x86_64/aarch64 or Windows x86_64) must match your system.
- Medium install friction due to platform-specific wheel distributions (Linux aarch64, Linux x86_64, Windows x86_64).
- Requires nvidia-nvjitlink as a runtime dependency.
License · maintenance · safety
(unclear)
last release 2026-06-29 (46 days)
0 known vulnerabilities (OSV.dev, 2026-08-14) · 42,085,601 downloads/mo, #661 on PyPI
Alternatives
Verify before relying
pip install nvidia-cusparse
import nvidia.cusparse
# Use CUSPARSE functions via the runtime library- Whether this package requires a local NVIDIA GPU or CUDA toolkit installation to function
- Specific CUDA compute capability requirements or version constraints beyond Python version support
- Whether nvidia-nvjitlink is automatically installed or must be manually configured
What it is and what it does
nvidia-cusparse is a runtime library package that bundles NVIDIA's CUSPARSE native libraries for GPU-accelerated sparse matrix operations. It serves as a dependency for higher-level libraries and frameworks that need to perform sparse linear algebra on NVIDIA GPUs. The package is classified as Beta and targets developers, educators, and researchers working with CUDA-based scientific computing and machine learning.
The package distributes platform-specific wheels for Linux (both x86_64 and aarch64) and Windows x86_64, with a single runtime dependency on nvidia-nvjitlink. Installation requires matching your system architecture to the available wheel; it does not provide Python-level APIs directly but rather makes the underlying CUSPARSE C libraries available to dependent packages.
Use it for
- Accelerate sparse matrix computations in machine learning frameworks that depend on CUSPARSE.
- Enable GPU-optimized linear algebra operations for scientific computing workloads.
- Provide native CUSPARSE bindings for deep learning libraries requiring sparse tensor support.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes, if you are building or using a CUDA-based application that requires sparse matrix operations and your system matches one of the supported platforms (Linux x86_64/aarch64 or Windows x86_64).
The package is actively maintained and has no known vulnerabilities. Install only if you have NVIDIA GPU hardware and the CUDA toolkit already set up; this is a runtime library, not a standalone tool.
Install
nvidia-cusparse on PyPI
Before you install
Medium install friction due to platform-specific wheel distributions (Linux aarch64, Linux x86_64, Windows x86_64). Requires nvidia-nvjitlink as a runtime dependency. Active maintenance with recent release history.
Requires NVIDIA GPU hardware and CUDA toolkit; platform-specific wheel (Linux x86_64/aarch64 or Windows x86_64) must match your system.
Quickstart
pip install nvidia-cusparse
import nvidia.cusparse
# Use CUSPARSE functions via the runtime libraryVerify before relying
- Whether this package requires a local NVIDIA GPU or CUDA toolkit installation to function
- Specific CUDA compute capability requirements or version constraints beyond Python version support
- Whether nvidia-nvjitlink is automatically installed or must be manually configured
Package facts
| License | Not declared unclear |
| Python support | Supports the current Python release >=3 |
| Install friction | Medium. Platform-specific wheel |
| Runtime dependencies | 1 packagenvidia-nvjitlink |
| Maintenance | Actively maintained 46 days since the last release |
| First released | |
| Downloads | 42,085,601 / month, #661 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | 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 |
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
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “gpu sparse linear algebra”
- nvidia-cusparseProvides NVIDIA CUSPARSE native runtime libraries for GPU-accelerated…
- pylibraft-cu12pylibraft-cu12 provides Python bindings to RAFT's CUDA-accelerated…
- onemkl-sycl-sparseProvides C and Data Parallel C++ (DPC++) interfaces to Intel's oneAPI…
Give your agent the search over MCP, or paste the wish link into any chat.
More Software Development packages
Provides backported and experimental type hints for Python 3.9+, allowing use of newer typing features on older Python versions and enabling early experimentation with type system PEPs before they enter the standard library.
NumPy provides an N-dimensional array object and a comprehensive suite of mathematical, linear algebra, Fourier transform, and random number functions for scientific computing in Python.
FastAPI is a Python web framework for building REST APIs using type hints, with automatic request validation, serialization, and interactive API documentation.
Provides a way to document function parameters, class attributes, return types, and variables inline using Python's `Annotated` type hint syntax instead of traditional docstrings.
Typer builds command-line applications from Python functions using type hints, automatically generating help text, argument parsing, and shell completion.
Install it if you are building CLIs in Python.
Distlib provides low-level packaging utilities for building, distributing, and managing Python software—including metadata handling, version specifiers, wheel support, script installation, and dependency resolution.
See also cuda-toolkit · nvidia-cusparse-cu11 · nvidia-cusparse-cu12 · nvidia-cublas · nvidia-cusolver · nvidia-cublas-cu12 · nvidia-cusparselt-cu13 · nvidia-cusolver-cu12 · nvidia-cusparselt-cu12 · fast-array-utils