NVIDIA Aerial™ CUDA-Accelerated RAN

Overview

NVIDIA Aerial™ CUDA-Accelerated RAN is an SDK (Software Development Kit) for building commercial-grade, AI-native, 3GPP, and O-RAN compliant 5G/6G gNB software on NVIDIA-accelerated computing platforms.

The SDK in this container includes:

• GPU-Accelerated 5G PHY (cuPHY): CUDA-based physical layer processing for 5G NR including channel coding (LDPC, Polar), modulation/demodulation, MIMO processing, and channel estimation

• GPU-Accelerated MAC Scheduler (cuMAC): High-performance L2 scheduler acceleration for resource allocation and scheduling

• Python API (pyAerial): Python bindings for AI/ML research and integration with frameworks like TensorFlow and Sionna

• 5G Reference Models (5GModel): MATLAB-based 5G waveform generation and test vector creation based on 3GPP specifications

NVIDIA Aerial™ CUDA-Accelerated RAN is a part of NVIDIA AI Aerial™, a portfolio of accelerated computing platforms, software and tools to build, train, simulate, and deploy AI-native wireless networks.

Getting Started

The SDK has components on GitHub and NGC.

Prerequisites

The following software components are required on the host:

• CUDA 13.1.1 driver (590.48.01)
• GDRCopy 2.5.1 (Not required for DGX Spark)
• Nvidia container toolkit:
  • https://github.com/NVIDIA/nvidia-docker
• Docker:
  • https://docs.docker.com/install/linux/docker-ce/ubuntu/
• Supported CPU, GPU and NIC combinations:
  • GH200: Grace Hopper MGX + BF3
  • DGX Spark: GB10 + CX7

Using Pre-Built Container (Recommended)

Clone repository

git clone https://github.com/NVIDIA/aerial-cuda-accelerated-ran.git --recurse-submodules
cd aerial-cuda-accelerated-ran

Enable git LFS (if needed for large files)

git lfs install
git lfs pull

Pull the Aerial container from NGC

docker pull nvcr.io/nvidia/aerial/aerial-cuda-accelerated-ran:26-1-cubb

Start interactive development container

./cuPHY-CP/container/run_aerial.sh

Inside container: Build SDK

./testBenches/phase4_test_scripts/build_aerial_sdk.sh

Further Information

Visit the full documentation at NVIDIA Docs Hub

Support

• File issues on GitHub for bugs and feature requests
• Join discussions for questions and community support

Acknowledgements

See Acknowledgements

Citation

If you use NVIDIA Aerial™ CUDA-Accelerated RAN in your research, please cite:

@software{nvidia_aerial_cuda_accelerated_ran,
  title = {NVIDIA Aerial™ CUDA-Accelerated RAN},
  author = {NVIDIA Corporation},
  year = {2025-2026},
  url = {https://github.com/NVIDIA/aerial-cuda-accelerated-ran}
}