NVIDIA Aerial™ Framework

Overview

NVIDIA Aerial™ Framework has been designed from the ground up to meet the needs of 3GPP Radio Access Networks — signal processing workloads with microsecond latency requirements. It is a single platform that unites research, testbeds, and production deployments to solve development challenges for real-time applications.

Use cases: Signal processing applications with strict latency requirements
Audience: RAN system engineers, signal processing specialists, AI researchers
Built with: DOCA, DPDK, TensorRT, Python, JAX, PyTorch, C++, CUDA, and more

The Aerial Framework combines two components:

• Developer tools: Tools to convert Python/JAX/PyTorch and C++/CUDA into pipelines of GPU-native code
• Runtime engine: Coordinates the execution of GPU pipelines with network interfaces

In addition to this container, source code is available on GitHub

NVIDIA Aerial™ Framework 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.

Quickstart

Install the Docker container, then explore and build from source:

# 1) Configure (release preset)
cmake --preset clang-release

# 2) Build
cmake --build out/build/clang-release

# 3) Install Example Python Package - 5G RAN
cd ran/py && uv sync

Documentation & Tutorials

Documentation is available at: docs.nvidia.com/aerial/framework

Get started with step-by-step Tutorials.

Support

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

Acknowledgements

See Acknowledgements

Citation

If you use NVIDIA Aerial™ Framework in your research, please cite:

@software{nvidia_aerial_framework,
  title = {NVIDIA Aerial™ Framework},
  author = {NVIDIA Corporation},
  year = {2025},
  url = {https://github.com/NVIDIA/aerial-framework}
}