Create Endpoints from docker images

In this guide, we'll show you how to create a dedicated endpoint from a docker image.

  1. Go to Endpoints tab and click on Create Endpoint
  2. Select Create Endpoint
  3. Select Create from Container Image
  4. For Endpoint name, you can set it to container-image-endpoint or any other name you like
  5. For Image configuration, you can select the docker image, command, and port you want to use.
    • Image: Choose the image you want to use. For demonstration, we can use nvcr.io/nvidia/pytorch:24.11-py3 as an example.
    • Server Port: Choose the port your process will listen on. For demonstration, we can use 8080 as an example.
    • Run command: Choose the command you want to run. For demonstration, we can use python -m http.server 8080 as an example.
    • Private image registry auth (optional): If you are using images from private registries, you can add the registry auth in registries page.
  6. For other configurations, you can leave it as default. You can refer to endpoint configurations for more details.
Note

It is recommended to have an access token setup for your endpoint instead of setting it as public.

Once the endpoint is created, you can see the created endpoint in the Endpoints tab. You can also view the logs from each replica by clicking on the logs button from replica section.

Copyright @ 2025, NVIDIA Corporation.