nvidia-nvvm

NVVM Libraries

nvidia-nvvm v13.3.73 2.3M downloads/30d#3,151 on PyPI

License unclear Active released 2026-06-29

What it is and what it does

nvidia-nvvm is a Python interface to NVIDIA's NVVM compiler IR library, the intermediate representation layer used to compile CUDA code for GPU execution. It sits between high-level CUDA C/C++ code and final GPU machine code, handling optimization and code generation for NVIDIA hardware.

The package is distributed as platform-specific wheels for Linux (x86_64 and aarch64) and Windows, indicating it bundles compiled binaries. It has no runtime dependencies and is in Beta status, supporting Python 3.5 through 3.11. It is intended for developers, educators, and researchers working on GPU-accelerated systems.

Use it for:

Building custom CUDA kernels or GPU code generation tools needing direct NVVM IR access
Developing machine learning frameworks that compile to GPU code
Creating GPU-accelerated libraries requiring low-level CUDA compilation
Integrating NVIDIA GPU compilation into Python-based build pipelines

Worth the install?

AI-flagged interpretation of the facts on this page — verify before relying

Provides the NVVM compiler IR library for building and optimizing CUDA applications on NVIDIA GPUs.

Yes, if you are developing CUDA applications or GPU-accelerated software and need programmatic access to NVIDIA's compiler IR. The package is actively maintained, has no known security vulnerabilities, and carries no documented license restrictions. Medium install friction is typical for platform-specific compiled bindings. Not relevant for non-GPU workloads.

Install

nvidia-nvvm on PyPI

pip

pip install nvidia-nvvm

uv

uv add nvidia-nvvm

poetry

poetry add nvidia-nvvm

Installing nvidia-nvvm

Before you install

Medium install friction due to platform-specific wheels for x86_64 Linux, aarch64 Linux, and Windows. Package is actively maintained with a release 46 days ago and supports current Python versions.

Quickstart

pip install nvidia-nvvm==13.3.73

import nvidia.nvvm
# Access NVVM compiler IR for CUDA code generation

Requires a compatible platform: x86_64 Linux, aarch64 Linux, or Windows. Python >=3 required.

Verify before relying

Whether this package requires a local CUDA toolkit installation or includes all necessary binaries
Whether the package works on macOS or is limited to Linux and Windows only
Documentation availability and API stability given Beta development status
Actual runtime dependencies or system-level prerequisites beyond the wheel distributions

Package facts

License	not declared (unclear)
Python support	supports the current Python release (>=3)
Install friction	medium — platform-specific wheel
Runtime dependencies	none
Maintenance	actively maintained — 46 days since the last release
First released	2025-08-04
Downloads	2,306,451/month — #3,151 on PyPI (30-day window, as of 2026-08-14)
Known vulnerabilities	none known (OSV.dev, checked 2026-08-14)

Evidence: nvidia_nvvm-13.3.73-py3-none-manylinux2010_x86_64.manylinux_2_12_x86_64.whl; nvidia_nvvm-13.3.73-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl; nvidia_nvvm-13.3.73-py3-none-win_amd64.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