nvidia-cufft-cu12
CUFFT native runtime libraries
Install
nvidia-cufft-cu12 on PyPI
pip
pip install nvidia-cufft-cu12uv
uv add nvidia-cufft-cu12poetry
poetry add nvidia-cufft-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-nvjitlink-cu12 |
| 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_cufft_cu12-11.4.1.4-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl; nvidia_cufft_cu12-11.4.1.4-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl; nvidia_cufft_cu12-11.4.1.4-py3-none-win_amd64.whl
Keywords: cuda, nvidia, runtime, machine learning, deep learning
About nvidia-cufft-cu12
from the package's own PyPI description — quoted content, verbatim
CUFFT 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 CUFFT (Compute Unified Fast Fourier Transform) native runtime libraries for GPU-accelerated FFT computations on CUDA 12 systems.
Medium install friction due to platform-specific wheel distributions (x86_64, aarch64, Windows). The package is aging (434 days since last release) with no repository metadata available for maintenance assessment, though it remains in the top 1000 PyPI packages.
Licensed under LicenseRef-NVIDIA-Proprietary with unclear treatment. This is a proprietary NVIDIA license; users should review NVIDIA's terms directly before deployment, particularly for commercial or redistributed applications.
Usage
pip install nvidia-cufft-cu12==11.4.1.4
import nvidia.cufft
# Use via higher-level CUDA libraries (e.g., CuPy, PyTorch) that depend on this runtime
Requires NVIDIA CUDA 12 toolkit and compatible GPU hardware; wheels are platform-specific (Linux x86_64/aarch64 or Windows x86_64 only).
Verdict: A foundational NVIDIA runtime library for GPU-accelerated FFT operations, suitable for machine learning and scientific computing workflows. The aging maintenance status and proprietary license warrant caution; this package is typically consumed as a transitive dependency rather than directly. No known security vulnerabilities, but verify NVIDIA's licensing terms for your use case.
Needs verification
- Whether the 434-day age represents normal NVIDIA release cadence or signals reduced support
- Compatibility matrix between this version and specific CUDA 12.x minor versions
- Whether the proprietary license permits commercial redistribution in your jurisdiction
Similar packages
unclear · top 1,000 on PyPI
nvidia-cufileunclear · top 1,000 on PyPI
nvidia-cuda-runtime-cu12unclear · top 1,000 on PyPI
nvidia-cuda-nvrtc-cu12unclear · top 1,000 on PyPI
nvidia-curand-cu12unclear · top 1,000 on PyPI
nvidia-cublas-cu12unclear · top 1,000 on PyPI
nvidia-cudnn-cu13unclear · top 1,000 on PyPI
nvidia-cuda-cupti-cu12unclear · top 1,000 on PyPI
nvidia-cusolver-cu12unclear · top 1,000 on PyPI
nvidia-cusparse-cu12unclear · top 1,000 on PyPI