nvidia-nvjitlink-cu12

Nvidia JIT LTO Library

nvidia-nvjitlink-cu12 License unclear LicenseRef-NVIDIA-Proprietary AGING v12.9.86 released 2025-06-05

Install

nvidia-nvjitlink-cu12 on PyPI

pip

pip install nvidia-nvjitlink-cu12

uv

uv add nvidia-nvjitlink-cu12

poetry

poetry add nvidia-nvjitlink-cu12

Package 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	2022-11-16
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_nvjitlink_cu12-12.9.86-py3-none-manylinux2010_x86_64.manylinux_2_12_x86_64.whl; nvidia_nvjitlink_cu12-12.9.86-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl; nvidia_nvjitlink_cu12-12.9.86-py3-none-win_amd64.whl

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

Development Status :: 4 - BetaIntended Audience :: DevelopersIntended Audience :: EducationIntended Audience :: Science/ResearchLicense :: Other/Proprietary LicenseNatural 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-nvjitlink-cu12

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

NVIDIA compiler library for JIT LTO functionality.

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's JIT LTO (Link Time Optimization) compiler library for CUDA 12, enabling runtime compilation and optimization of GPU code.

Medium install friction due to platform-specific wheels (x86_64 Linux, ARM64 Linux, Windows); no runtime dependencies. Package is aging (434 days since last release) with Beta status, suggesting limited active maintenance.

Licensed under LicenseRef-NVIDIA-Proprietary with unclear treatment; this is a proprietary NVIDIA library with non-standard SPDX classification, so commercial or redistributive use requires careful review of NVIDIA's terms.

Usage

pip install nvidia-nvjitlink-cu12==12.9.86
import nvidia.nvjitlink
# Use within CUDA-enabled GPU code compilation workflows

Requires CUDA 12 toolkit and compatible GPU hardware; platform-specific wheel must match your OS (Linux x86_64, Linux ARM64, or Windows x86_64).

Verdict: A low-level NVIDIA compiler runtime library for GPU JIT compilation, with no external dependencies but medium install friction from platform specificity. Aging maintenance status and proprietary licensing make it suitable primarily for projects already committed to CUDA 12 ecosystems; verify compatibility with your target deployment platform before adoption.

Needs verification

Whether this package is intended for direct end-user installation or primarily as a transitive dependency of higher-level CUDA libraries.
Specific terms and restrictions of the NVIDIA proprietary license and whether commercial use requires additional licensing.
Whether the 434-day gap since last release reflects stable maturity or abandonment relative to CUDA 12 LTS support.

nvidia cuda jit compilationgpu runtime compilernvidia nvjitlinkcuda link time optimizationgpu code jit compilation