nvidia-cuda-nvrtc-cu12
NVRTC native runtime libraries
Install
nvidia-cuda-nvrtc-cu12 on PyPI
pip
pip install nvidia-cuda-nvrtc-cu12uv
uv add nvidia-cuda-nvrtc-cu12poetry
poetry add nvidia-cuda-nvrtc-cu12Package facts
| License | LicenseRef-NVIDIA-Proprietary (unclear) |
| Python support | supports the current Python release (>=3) |
| Install friction | medium — platform-specific wheel |
| Runtime dependencies | none |
| Maintenance | aging — 434 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_cuda_nvrtc_cu12-12.9.86-py3-none-manylinux2010_x86_64.manylinux_2_12_x86_64.whl; nvidia_cuda_nvrtc_cu12-12.9.86-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl; nvidia_cuda_nvrtc_cu12-12.9.86-py3-none-win_amd64.whl
Keywords: cuda, nvidia, runtime, machine learning, deep learning
About nvidia-cuda-nvrtc-cu12
from the package's own PyPI description — quoted content, verbatim
NVRTC 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 CUDA NVRTC (runtime compilation) native libraries for GPU-accelerated compute, enabling just-in-time compilation of CUDA kernels.
Medium install friction due to platform-specific wheels (x86_64 Linux, ARM64 Linux, Windows x64 only). Package is aging—434 days since last release—with no visible repository activity, raising questions about maintenance responsiveness.
Licensed under LicenseRef-NVIDIA-Proprietary with unclear treatment. NVIDIA's proprietary license terms are not SPDX-standardized, so review NVIDIA's licensing documentation directly before use in commercial or redistributed contexts.
Usage
pip install nvidia-cuda-nvrtc-cu12==12.9.86
import nvidia.cuda_nvrtc
Requires CUDA 12.x-compatible GPU and Linux (x86_64/ARM64) or Windows x64; not available for macOS or other architectures.
Verdict: A foundational NVIDIA library for GPU compute with no known vulnerabilities and broad Python version support (3.5+). However, its aging maintenance status (434 days), proprietary license with unclear terms, and platform-specific availability make it a dependency best evaluated as part of a larger CUDA ecosystem rather than as a standalone choice.
Needs verification
- Whether NVIDIA actively maintains this package or has shifted maintenance to a different distribution channel.
- Specific licensing restrictions on commercial use, redistribution, or bundling with proprietary software.
- Whether the package works correctly with Python 3.5–3.9 despite being released in 2022 and updated in 2025.
Similar packages
unclear · top 1,000 on PyPI
nvidia-nvjitlink-cu12unclear · top 1,000 on PyPI
nvidia-cufft-cu12unclear · top 1,000 on PyPI
nvidia-cublas-cu12unclear · top 1,000 on PyPI
nvidia-cusparse-cu12unclear · top 1,000 on PyPI
nvidia-cuda-runtime-cu12unclear · top 1,000 on PyPI
tritonpermissive · top 1,000 on PyPI
lightgbmunclear · top 1,000 on PyPI
nvidia-nvjitlinkunclear · top 1,000 on PyPI
numbapermissive · top 1,000 on PyPI