4. Deployments

Each running model service is defined as a "Deployment". There can be multiple deployments running simultaneously depending on the number of models and inference resource (GPUs & CPU).

Deployment list

Here is the Deployment list, showing all deployments and their status, users can edit/stop or delete deployments

To create a new deployment just click on the "DEPLOY MODEL" button, or select "Deploy" from the model list in 3. Models

Last updated