nvidia-cublas-cu12
CUBLAS native runtime libraries
Install
nvidia-cublas-cu12 on PyPI
pip
pip install nvidia-cublas-cu12uv
uv add nvidia-cublas-cu12poetry
poetry add nvidia-cublas-cu12Package 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-cu12 |
| Maintenance | actively maintained — 127 days since the last release |
| First released | |
| 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_cu12-12.9.2.10-py3-none-manylinux_2_27_aarch64.whl; nvidia_cublas_cu12-12.9.2.10-py3-none-manylinux_2_27_x86_64.whl; nvidia_cublas_cu12-12.9.2.10-py3-none-win_amd64.whl
Keywords: cuda, nvidia, runtime, machine learning, deep learning
About nvidia-cublas-cu12
from the package's own PyPI description — quoted content, verbatim
CUBLAS native runtime libraries
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 CUDA 12, enabling GPU-accelerated linear algebra operations in Python applications on supported platforms.
Medium install friction due to platform-specific wheel distributions (x86_64, aarch64, Windows); requires nvidia-cuda-nvrtc-cu12 at runtime. Package is actively maintained with a recent release cycle.
Licensed under LicenseRef-NVIDIA-Proprietary with unclear treatment; users should review NVIDIA's proprietary license terms before deployment, particularly in commercial or redistributed contexts.
Usage
pip install nvidia-cublas-cu12==12.9.2.10
import nvidia.cublas.cu12
# CUBLAS functions available through nvidia-cuda-nvrtc-cu12 dependency
Requires NVIDIA CUDA 12 compatible GPU and driver; only wheels available for Linux (x86_64, aarch64) and Windows (amd64).
Verdict: A specialized runtime library for GPU-accelerated linear algebra in the CUDA 12 ecosystem. Active maintenance and zero known vulnerabilities are positive signals, but the proprietary license status and platform-specific installation requirements demand careful evaluation before adoption. Best suited for teams already committed to NVIDIA GPU infrastructure.
Needs verification
- Whether the proprietary license permits commercial use or redistribution without additional licensing agreements.
- Compatibility matrix with specific NVIDIA driver versions and CUDA Compute Capability levels.
- Performance characteristics or benchmarks compared to alternative CUBLAS distributions.
Similar packages
unclear · top 1,000 on PyPI
nvidia-cufileunclear · top 1,000 on PyPI
nvidia-cusolver-cu12unclear · top 1,000 on PyPI
cuda-toolkitunclear · top 1,000 on PyPI
nvidia-cusparse-cu12unclear · top 1,000 on PyPI
nvidia-cuda-runtime-cu12unclear · top 1,000 on PyPI
nvidia-cuda-nvrtcunclear · top 1,000 on PyPI
nvidia-cusparseunclear · top 1,000 on PyPI
nvidia-cuda-runtimeunclear · top 1,000 on PyPI
nvidia-cusolverunclear · top 1,000 on PyPI