Skip to main content

Sionna - A hardware-accelerated differentiable open-source library for research on communication systems

Project description

Sionna 2.0: An Open-Source Library for Research on Communication Systems

Sionna™ is an open-source Python-based library for research on communication systems.

The official documentation can be found here.

It is composed of the following packages:

  • Sionna RT - A lightning-fast stand-alone ray tracer for radio propagation modeling

  • Sionna PHY - A link-level simulator for wireless and optical communication systems

  • Sionna SYS - A system-level simulator based on physical-layer abstraction

Installation

Sionna PHY and Sionna SYS require Python 3.11+ and PyTorch 2.9+. We recommend Ubuntu 24.04. Earlier versions of PyTorch may still work but are not recommended. We refer to the PyTorch get-started guide for GPU (CUDA) support and the required driver setup.

Sionna RT has the same requirements as Mitsuba 3 and we refer to its installation guide for further information. To run Sionna RT on CPU, LLVM is required by Dr.Jit. Please check the installation instructions for the LLVM backend. The source code of Sionna RT is located in a separate GitHub repository.

If you want to run the tutorial notebooks on your machine, you also need JupyterLab. You can alternatively test them on Google Colab. Although not necessary, we recommend running Sionna in a Docker container and/or Python virtual enviroment.

Installation via pip

The recommended way to install Sionna is via pip:

pip install sionna

If you want to install only Sionna RT, run:

pip install sionna-rt

You can install Sionna without the RT package via

pip install sionna-no-rt

Installation from source

  1. Clone the repository with all submodules:
    git clone --recursive https://github.com/NVlabs/sionna
    
    If you have already cloned the repository but forgot to set the --recursive flag, you can correct this via:
    git submodule update --init --recursive --remote
    
  2. Install Sionna (including Sionna RT) by running the following command from within the repository's root folder:
    pip install ext/sionna-rt/ .
    pip install .
    

Testing

First, you need to install the test requirements by executing the following command from the repository's root directory:

pip install '.[test]'

The unit tests can then be executed by running pytest from within the test folder.

Building the Documentation

Install the requirements for building the documentation by running the following command from the repository's root directory:

pip install '.[doc]'

You might need to install pandoc manually.

You can then build the documentation by executing make html from within the doc folder.

To serve the documentation locally:

make serve

This serves the documentation at http://localhost:8000/sionna/ with the same URL structure as the production website. You can specify a different port with make serve PORT=9000.

For local development without the /sionna/ prefix, build and serve with:

BASE_PATH= make html
BASE_PATH= make serve

License and Citation

Sionna is Apache-2.0 licensed, as found in the LICENSE file.

If you use this software, please cite it as:

@software{sionna,
 title = {Sionna},
 author = {Hoydis, Jakob and Cammerer, Sebastian and {Ait Aoudia}, Fayçal and Nimier-David, Merlin and Maggi, Lorenzo and Marcus, Guillermo and Vem, Avinash and Keller, Alexander},
 note = {https://nvlabs.github.io/sionna/},
 year = {2022},
 version = {2.0.1}
}

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

sionna-2.0.1-py3-none-any.whl (562.1 kB view details)

Uploaded Python 3

File details

Details for the file sionna-2.0.1-py3-none-any.whl.

File metadata

  • Download URL: sionna-2.0.1-py3-none-any.whl
  • Upload date:
  • Size: 562.1 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.14.3

File hashes

Hashes for sionna-2.0.1-py3-none-any.whl
Algorithm Hash digest
SHA256 87b1574de0163531509df636986d7b87c88e922b06232feb205661a354f94a0b
MD5 b173596448bbcce6997ca00242377985
BLAKE2b-256 b421f5f0bc95ac66405fc82b9fbad50e9d5d35f1bdc65627f0cf93736a2dd4d8

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page