nvidia-cublas

CUBLAS native runtime libraries

nvidia-cublas License unclear LicenseRef-NVIDIA-Proprietary Active v13.6.1.10 released 2026-07-30

Install

nvidia-cublas on PyPI

pip

pip install nvidia-cublas

uv

uv add nvidia-cublas

poetry

poetry add nvidia-cublas

Package facts

License	LicenseRef-NVIDIA-Proprietary (unclear)
Python support	supports the current Python release (>=3)
Install friction	medium — platform-specific wheel
Runtime dependencies	1 — nvidia-cuda-nvrtc
Maintenance	actively maintained — 14 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_cublas-13.6.1.10-py3-none-manylinux_2_27_aarch64.whl; nvidia_cublas-13.6.1.10-py3-none-manylinux_2_27_x86_64.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-cublas

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

CUBLAS 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 CUBLAS native runtime libraries for GPU-accelerated linear algebra operations on CUDA-capable hardware.

Active maintenance with a recent release (14 days old). Medium install friction due to platform-specific wheels for x86_64 and aarch64 Linux; requires nvidia-cuda-nvrtc as a runtime dependency.

Licensed under LicenseRef-NVIDIA-Proprietary with unclear treatment; users should review NVIDIA's licensing terms before deployment, particularly in commercial or redistributed contexts.

Usage

pip install nvidia-cublas==13.6.1.10
import nvidia.cublas
# Use CUBLAS functions via nvidia-cuda-nvrtc integration

Requires NVIDIA CUDA-capable GPU and compatible CUDA Toolkit; only available for Linux (x86_64, aarch64) and Windows.

Verdict: A well-maintained, actively developed GPU acceleration library in the top 1000 PyPI packages with no known vulnerabilities. Medium install friction and proprietary licensing are the primary considerations; suitable for machine learning and scientific computing workflows on supported platforms.

Needs verification

Whether the proprietary license permits commercial use without additional licensing agreements.
Specific CUDA Toolkit version compatibility requirements beyond the runtime dependency.
Performance characteristics and whether this is the recommended path versus conda/NVIDIA's official distributions.

cuda linear algebra gpunvidia cublas runtimegpu matrix operationscuda blas librarynvidia gpu accelerationdeep learning gpu computecuda math library