In order to use Riva AI Services, you are required to be logged in to NVIDIA GPU Cloud (NGC).
You have access to a Volta, Turing, or an NVIDIA Ampere architecture-based GPU.
Download Riva quick start scripts via the command-line with the NGC CLI tool by running the CLI command above or selecting the File Browser tab to download the scripts.
Initialize and start Riva. The initialization step downloads and prepares Docker images and models. The start script launches the server.
Note: This process may take quite some time depending on the speed of your Internet connection and the number of models deployed. Each model is individually optimized for the target GPU after download.
cd riva_quickstart_v1.7.0-beta bash riva_init.sh bash riva_start.sh
Start a container with sample clients for each service.
From inside the client container, try the different services using the provided Jupyter notebooks.
jupyter notebook --ip=0.0.0.0 --allow-root --notebook-dir=/work/notebooks
quickstart directory, you can modify the
config.sh file with your preferred configuration. Options include which models to retrieve from NGC, where to store them, and which GPU to use if more than one is installed in your system (see Local (Docker) for more details).
To view and download the full list of components included as part of Riva, refer to the Riva Collection.
For the latest release specific documentation, refer to the Release Notes.
For a full list of the supported hardware and software, refer to the Support Matrix.
For all other documentation, refer to the User Guide.
By pulling and using Riva software, you accept the terms and conditions of this license.