---
id: cuequivariance-ops-cu12
version: "0.11.1"
license: # Software License Agreement LICENSE AGREEMENT FOR NVIDIA MATH LIBRARIES SOFTWARE DEVELOPMENT KITS This license agreement(“Agreement”) is a legal agreement between you and NVIDIA Corporation… (full text in the JSON record)
license_treatment: unclear
maintenance: active
---

# cuequivariance-ops-cu12 — cuequivariance-ops - GPU Accelerated Extensions for Equivariant Primitives

License: unclear · Maintenance: active · Downloads: 119.4K/mo

## What it is and what it does

cuequivariance-ops-cu12 is a compiled CUDA kernel library for equivariant neural network primitives, distributed as a Python package that loads pre-built binary extensions at import time. It contains no Python source code—only a shared library wrapper that exposes GPU-accelerated operations for the cuEquivariance framework. The package is designed to run on NVIDIA GPUs and depends on CUDA 12.x runtime libraries (nvidia-cublas-cu12) plus standard Python utilities for progress reporting and platform detection.

This is a low-level infrastructure package: developers do not call it directly, but rather use it as a runtime dependency of higher-level equivariance libraries. Installation is restricted to Linux (x86_64 and aarch64 architectures) and requires Python 3.10 or later. The NVIDIA proprietary license permits use only on NVIDIA GPU systems and prohibits reverse engineering, sublicensing, or derivative works without explicit permission.

Use it for:

- Accelerate equivariant neural network training and inference on NVIDIA GPUs via the cuEquivariance library
- Deploy production models that require equivariant primitives with GPU performance on NVIDIA hardware
- Research equivariant deep learning with access to optimized CUDA kernels for group-equivariant operations
- Build AI applications requiring geometric or symmetry-preserving neural network layers on NVIDIA systems

## Worth the install?

AI-flagged interpretation of the facts above — verify before relying.

Loads CUDA kernels for equivariant neural network operations on NVIDIA GPUs, providing compiled binary extensions without Python bindings.

Yes, if you are using cuEquivariance on an NVIDIA GPU system and require GPU acceleration for equivariant operations. Install only on Linux (x86_64 or aarch64) with Python >=3.10 and CUDA 12.x runtime. The NVIDIA proprietary license is restrictive—do not use if you need to redistribute or modify the library. No known security vulnerabilities as of the query date.

## Install

pip install cuequivariance-ops-cu12
uv add cuequivariance-ops-cu12
poetry add cuequivariance-ops-cu12

## Installing cuequivariance-ops-cu12

Before you install: Medium install friction due to platform-specific wheels (x86_64 and aarch64 Linux only). Active maintenance with recent release. Requires NVIDIA CUDA runtime dependencies (nvidia-cublas-cu12, nvidia-ml-py) and standard utilities (tqdm, platformdirs).

License in practice: NVIDIA proprietary license with significant restrictions: SDK licensed only for NVIDIA GPU systems, prohibits reverse engineering, restricts sublicensing and derivative works, and requires material additional functionality if distributed. Liability capped at $10.00 USD. Not suitable for open-source or unrestricted redistribution.

Quickstart:

pip install cuequivariance-ops-cu12
import cuequivariance_ops_cu12
# Loads CUDA kernels for use by cuEquivariance library

Requires NVIDIA GPU, CUDA 12.x runtime, and Linux (x86_64 or aarch64). Python >=3.10 required.

Verify before relying:

- Whether this package is meant to be used standalone or only as a dependency of cuEquivariance itself
- What specific equivariant operations the CUDA kernels implement
- Performance characteristics or benchmarks relative to CPU or other GPU implementations

## Package facts

- License: # Software License Agreement LICENSE AGREEMENT FOR NVIDIA MATH LIBRARIES SOFTWARE DEVELOPMENT KITS This license agreement(“Agreement”) is a legal agreement between you and NVIDIA Corporation… (full text in the JSON record) (unclear)
- Python support: supports_current
- Install friction: medium
- Maintenance: active
- Downloads: 119.4K/month (top 15,000 on PyPI)
- Known vulnerabilities: none known

## Tags

cuda kernels equivariant neural networks, gpu accelerated equivariance primitives, nvidia cuequivariance cuda extensions, equivariant deep learning gpu, cuda math libraries gpu computing, equivariant neural network acceleration, cuda-kernels, equivariant-networks, gpu-acceleration

[View on SkillFed](https://skillfed.io/packages/cuequivariance-ops-cu12) · [View on PyPI](https://pypi.org/project/cuequivariance-ops-cu12/)