cuequivariance-ops-cu12
cuequivariance-ops - GPU Accelerated Extensions for Equivariant Primitives
Decision gist · record as of 2026-08-14
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.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires NVIDIA GPU, CUDA 12.x runtime, and Linux (x86_64 or aarch64).
- Python >=3.10 required.
- Medium install friction due to platform-specific wheels (x86_64 and aarch64 Linux only).
License · maintenance · safety
(unclear) — 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.
last release 2026-08-07 (7 days)
0 known vulnerabilities (OSV.dev, 2026-08-14) · 119,360 downloads/mo, #12,076 on PyPI
Alternatives
Verify before relying
pip install cuequivariance-ops-cu12
import cuequivariance_ops_cu12
# Loads CUDA kernels for use by cuEquivariance library- 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
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 on this page. Verify before relying on it.
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
cuequivariance-ops-cu12 on PyPI
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).
Requires NVIDIA GPU, CUDA 12.x runtime, and Linux (x86_64 or aarch64). Python >=3.10 required.
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 libraryVerify 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 | Not declared unclear |
| Python support | Supports the current Python release >=3.10 |
| Install friction | Medium. Platform-specific wheel |
| Runtime dependencies | 4 packagesnvidia-cublas-cu12tqdmnvidia-ml-pyplatformdirs |
| Maintenance | Actively maintained 7 days since the last release |
| First released | |
| Downloads | 119,360 / month, #12,076 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Intended Audience :: DevelopersProgramming Language :: Python |
Evidence: cuequivariance_ops_cu12-0.11.1-py3-none-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl; cuequivariance_ops_cu12-0.11.1-py3-none-manylinux_2_24_x86_64.manylinux_2_28_x86_64.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 accelerated equivariance primitives”
- cuequivariance-ops-cu12Loads CUDA kernels for equivariant neural network operations on…
- cuequivariance-ops-cu13Provides CUDA kernels for equivariant neural network operations,…
- cuequivariance-torchPyTorch bindings for NVIDIA's CUDA-accelerated library for building…
Give your agent the search over MCP, or paste the wish link into any chat.
More Artificial Intelligence packages
LiteLLM provides a unified Python interface to call 100+ LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Azure, and others) using OpenAI-compatible API format, available as both a Python SDK and a self-hosted AI Gateway proxy server.
Install it if you need to work with multiple LLM providers or want to centralize LLM routing in your organization.
Client library and CLI tool for downloading, uploading, and managing models, datasets, and repositories on the Hugging Face Hub platform.
Install it if you work with Hugging Face Hub models or datasets.
LangChain provides a framework for building agents and LLM-powered applications by composing language models, tools, and memory through a unified API that abstracts over multiple model providers.
hf-xet provides chunk-based deduplication and efficient file transfer for the Hugging Face Hub, enabling faster uploads and downloads of large files with local disk caching.
Tokenizers converts raw text into token sequences for NLP models, with support for training custom vocabularies and using pre-built tokenizers (BPE, WordPiece) optimized for speed via Rust.
Transformers provides a unified framework for loading, fine-tuning, and running state-of-the-art pretrained models across text, vision, audio, video, and multimodal tasks using PyTorch, JAX, or TensorFlow.
Install it if you need to run or train any transformer-based model for NLP, vision, audio, or multimodal tasks.
See also cuequivariance-ops-cu13 · cuequivariance-ops-torch-cu12 · cuequivariance-torch · cuequivariance · nvidia-cudnn-cu12 · nvidia-cudnn-cu11 · nvidia-cusparse-cu12 · nvidia-cublas-cu12 · nvidia-cudnn-cu13 · nvidia-cublas-cu11