nvidia-libnvcomp-cu12
NVIDIA nvcomp for CUDA 12
Decision gist · record as of 2026-08-14
Yes, if you have CUDA 12 and an NVIDIA GPU and need high-performance lossless compression. The package is actively maintained, has no known vulnerabilities, and fills a specific niche. However, verify that your platform (Linux aarch64/x86_64 or Windows amd64) is supported and that the proprietary NVIDIA SDK license terms are acceptable for your use case.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires CUDA 12 runtime and compatible GPU; platform-specific wheels limit installation to Linux (aarch64/x86_64) or Windows (amd64).
- Medium install friction due to platform-specific wheels (aarch64, x86_64, Windows); requires compatible CUDA 12 environment.
- Package is actively maintained with recent releases.
License · maintenance · safety
(unclear) — Licensed under NVIDIA's proprietary SDK agreement rather than a standard open-source license; users must review the LICENSE AGREEMENT FOR NVIDIA SOFTWARE DEVELOPMENT KITS terms before use.
last release 2026-07-14 (31 days)
0 known vulnerabilities (OSV.dev, 2026-08-14) · 313,485 downloads/mo, #7,713 on PyPI
Alternatives
Verify before relying
pip install nvidia-libnvcomp-cu12
import nvidia.libnvcomp_cu12- Specific Python version compatibility (requires_python unspecified in metadata)
- Whether the package provides a public Python API or is primarily a compiled library wrapper
- Documentation and example usage availability beyond the NVIDIA developer homepage
What it is and what it does
nvidia-libnvcomp-cu12 is NVIDIA's GPU-accelerated compression library packaged for CUDA 12. It exposes fast lossless compression and decompression routines that run on NVIDIA GPUs, allowing developers to offload compression workloads from CPU to GPU for performance-critical applications. The library provides generic compression interfaces designed to integrate into existing applications that need high-throughput data compression.
The package is a compiled binary distribution (wheels for Linux aarch64/x86_64 and Windows amd64) with no runtime Python dependencies. Installation requires a compatible CUDA 12 environment and an NVIDIA GPU. It is actively maintained and has seen recent releases.
Use it for
- Compress large datasets on GPU before network transmission or storage in data pipeline applications.
- Accelerate backup and archival workflows by offloading compression to GPU hardware.
- Integrate GPU compression into machine learning frameworks that process large batches of data.
- Reduce CPU overhead in real-time data processing systems by using GPU compression.
- Optimize memory-to-disk I/O in scientific computing applications with GPU-accelerated compression.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes, if you have CUDA 12 and an NVIDIA GPU and need high-performance lossless compression.
The package is actively maintained, has no known vulnerabilities, and fills a specific niche. However, verify that your platform (Linux aarch64/x86_64 or Windows amd64) is supported and that the proprietary NVIDIA SDK license terms are acceptable for your use case.
Install
nvidia-libnvcomp-cu12 on PyPI
Before you install
Medium install friction due to platform-specific wheels (aarch64, x86_64, Windows); requires compatible CUDA 12 environment. Package is actively maintained with recent releases.
Requires CUDA 12 runtime and compatible GPU; platform-specific wheels limit installation to Linux (aarch64/x86_64) or Windows (amd64).
License in practice
Licensed under NVIDIA's proprietary SDK agreement rather than a standard open-source license; users must review the LICENSE AGREEMENT FOR NVIDIA SOFTWARE DEVELOPMENT KITS terms before use.
Quickstart
pip install nvidia-libnvcomp-cu12
import nvidia.libnvcomp_cu12Verify before relying
- Specific Python version compatibility (requires_python unspecified in metadata)
- Whether the package provides a public Python API or is primarily a compiled library wrapper
- Documentation and example usage availability beyond the NVIDIA developer homepage
Package facts
| License | Not declared unclear |
| Python support | Not specified |
| Install friction | Medium. Platform-specific wheel |
| Runtime dependencies | None |
| Maintenance | Actively maintained 31 days since the last release |
| First released | |
| Downloads | 313,485 / month, #7,713 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
Evidence: nvidia_libnvcomp_cu12-5.3.0.16-py3-none-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl; nvidia_libnvcomp_cu12-5.3.0.16-py3-none-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl; nvidia_libnvcomp_cu12-5.3.0.16-py3-none-win_amd64.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “gpu compression decompression”
- nvidia-libnvcomp-cu12Provides GPU-accelerated lossless data compression and decompression…
- xpress8xpress8 provides Python bindings to Microsoft's Xpress8 compression…
- brotlicffiProvides Python CFFI bindings to the Brotli compression library,…
Give your agent the search over MCP, or paste the wish link into any chat.
More Scientific/Engineering packages
NumPy provides an N-dimensional array object and a comprehensive suite of mathematical, linear algebra, Fourier transform, and random number functions for scientific computing in Python.
pandas provides fast, flexible data structures (Series and DataFrame) for loading, cleaning, transforming, and analyzing labeled or relational data in Python.
scipy provides numerical algorithms for mathematics, science, and engineering—including optimization, integration, linear algebra, Fourier transforms, signal and image processing, and ODE solvers—built on numpy arrays.
scikit-learn provides a comprehensive Python library for supervised and unsupervised machine learning, including classification, regression, clustering, dimensionality reduction, and model evaluation tools built on NumPy and SciPy.
Install it if you need to train, evaluate, or deploy supervised or unsupervised learning models.
dill extends Python's pickle module to serialize and deserialize a much wider range of Python objects, including functions, lambdas, classes, and interpreter sessions, to byte streams for storage or network transmission.
Multiprocess is an enhanced fork of Python's standard multiprocessing library that uses dill for better serialization, allowing you to spawn processes with a threading-like API and share complex objects between them.
Install it if you use multiprocessing and encounter pickle serialization limits with lambdas or complex objects.
See also nvidia-nvimgcodec-cu12 · nvidia-cusolver-cu11 · nvidia-cusparse-cu12 · nvidia-cudnn-cu12 · nvidia-cusolver-cu12 · custatevec-cu12 · libkvikio-cu12 · nvidia-cublas-cu12 · nvidia-cusolver · custatevec-cu13