nvidia-cufft

CUFFT native runtime libraries

nvidia-cufft License unclear Active v12.3.0.29 released 2026-05-26

Install

nvidia-cufft on PyPI

pip

pip install nvidia-cufft

uv

uv add nvidia-cufft

poetry

poetry add nvidia-cufft

Package facts

License	not declared (unclear)
Python support	supports the current Python release (>=3)
Install friction	medium — platform-specific wheel
Runtime dependencies	1 — nvidia-nvjitlink
Maintenance	actively maintained — 79 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_cufft-12.3.0.29-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl; nvidia_cufft-12.3.0.29-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl; nvidia_cufft-12.3.0.29-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

About nvidia-cufft

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

CUFFT 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 CUFFT native runtime libraries for GPU-accelerated Fast Fourier Transform computations on CUDA-capable hardware.

Medium install friction due to platform-specific wheels (x86_64, aarch64, Windows); requires nvidia-nvjitlink at runtime. Package is actively maintained with a recent release (79 days old).

License treatment is unclear—no SPDX identifier or raw license text is declared. Verify licensing terms directly with NVIDIA before use in proprietary or redistributed contexts.

Usage

pip install nvidia-cufft==12.3.0.29
import nvidia.cufft
# Use via higher-level CUDA libraries (e.g., CuPy, PyTorch)

Requires NVIDIA CUDA Compute Capability 3.5+ GPU and nvidia-nvjitlink runtime dependency installed.

Verdict: A foundational NVIDIA runtime library for GPU-accelerated FFT operations, actively maintained and free of known vulnerabilities. Medium install friction stems from platform-specific wheels and the nvidia-nvjitlink dependency. Primary concern is unclear licensing—verify NVIDIA's terms before adoption in commercial or redistributed projects.

Needs verification

Whether this package is intended for direct use or only as a transitive dependency of higher-level libraries
Specific NVIDIA license terms and any restrictions on redistribution or commercial use
Compatibility matrix across CUDA versions and GPU architectures beyond the wheel platforms listed

nvidia cufft gpu fftcuda fast fourier transformgpu accelerated fft librarynvidia cufft runtimecuda fft accelerationgpu signal processingnvidia cuda math libraries