# NVlabs/sionna

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

Repository: https://github.com/NVlabs/sionna
Canonical: https://ross.abutalabs.com/products/sionna
Homepage: https://nvlabs.github.io/sionna/
Language: Jupyter Notebook
License: NOASSERTION
License Family: other
Topics: communications, 5g, 6g, machine-learning, deep-learning, link-level-simulation, reproducible-research, open-source, gpu-acceleration, raytracing, system-level-simulation, differentiable-simulation
Last push: 2026-07-01T17:10:45+00:00

## Health v2 (maintenance only)
Score: 83/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 90, release rhythm 65, longevity 100
- inputs: {"age_days": 1660, "days_push": 63, "days_rel": 154, "gap_med": 43.0, "n_releases_24m": 11}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1577, forks 409 (observed 2026-08-28T04:05:06.082200+00:00)

## What it is
Sionna is an open-source, GPU-accelerated, differentiable Python library from NVIDIA for research on communication systems. It comprises Sionna RT (a ray tracer for radio propagation modeling), Sionna PHY (a link-level simulator for wireless and optical systems), and Sionna SYS (a system-level simulator), all built on PyTorch, Mitsuba 3, and Dr.Jit.

## Use cases
- simulate 5G and 6G wireless communication systems
- ray trace radio propagation in 3D scenes
- run link-level simulations of physical layer algorithms
- integrate neural networks into communication system pipelines
- perform gradient-based optimization of communication components
- model wireless channels with differentiable simulation
- prototype communication system architectures in Jupyter notebooks
- deploy trained AI/ML components in a software-defined 5G RAN

## When to choose
- you need GPU-accelerated, differentiable simulation of wireless or optical communication systems
- you are doing 5G/6G physical-layer or system-level research with machine learning
- you want to ray trace radio propagation for channel modeling
- you want reproducible, modular building blocks for communication system prototyping

## When to avoid
- you need a production network planning or deployment tool rather than a research library
- you require a license other than Apache-2.0 or need commercial support guarantees
- you work without Python/PyTorch and need a standalone GUI simulator
- your focus is general-purpose rendering rather than radio propagation

## Facets
- artifact type: library
- maturity: active
- function: simulation, machine-learning, deep-learning, gpu-computing, graphics
- domain: simulation, machine-learning, gpu-computing
- platform: python, cross-platform
- tags: 5g, 6g, ray-tracing, link-level-simulation, system-level-simulation, differentiable-simulation, radio-propagation, wireless-communication, pytorch, reproducible-research, telecommunications, research, linux, gpu

## Member repositories
- NVlabs/sionna (main) score 83

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:06.082200+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:57:01.844882+00:00, confidence not recorded.
  - readme: https://github.com/NVlabs/sionna (fetched 2026-08-28T04:05:06.082200+00:00, sha 649c5b7ab505)
  - homepage: https://nvlabs.github.io/sionna/ (fetched 2026-08-29T11:27:22.120679+00:00, sha c781347bd2be)
  - registry_pypi: https://pypi.org/pypi/sionna/json (fetched 2026-08-29T11:27:22.129439+00:00, sha dd45a31d7040)
- Data as of 2026-08-30T08:39:29.467469+00:00.