skillfed

nvidia-libnvcomp-cu12

NVIDIA nvcomp for CUDA 12

nvidia-libnvcomp-cu12 v5.3.0.16 313.5K downloads/30d#7,713 on PyPI
License unclear LICENSE AGREEMENT FOR NVIDIA SOFTWARE DEVELOPMENT KITS Active released

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

Provides GPU-accelerated lossless data compression and decompression using NVIDIA CUDA 12, enabling high-performance compression operations in applications through a generic compression interface.

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

pip

pip install nvidia-libnvcomp-cu12

uv

uv add nvidia-libnvcomp-cu12

poetry

poetry add nvidia-libnvcomp-cu12

Installing nvidia-libnvcomp-cu12

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.

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_cu12

Requires CUDA 12 runtime and compatible GPU; platform-specific wheels limit installation to Linux (aarch64/x86_64) or Windows (amd64).

Verify 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 LICENSE AGREEMENT FOR NVIDIA SOFTWARE DEVELOPMENT KITS (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

gpu compression decompressionnvidia cuda compression librarylossless gpu compressionnvcomp cuda 12gpu accelerated data compressionhigh performance compression gpunvidia nvcomp library
gpu-accelerationcompressioncuda

More Scientific/Engineering packages

Further reading