To scale the performance of Domino endpoints in Domino, you can scale hardware using Domino endpoint hardware tiers, or increase the degree of parallelism.
Use Domino endpoint hardware tiers to scale your models deployed as Domino endpoints.
Since Domino endpoints often have different requirements than Workspaces and Jobs, Domino lets you classify specific hardware tiers for Domino endpoints, allowing you to tailor your hardware to meet the unique demands of machine learning model deployment.
|
Note
| Domino endpoint tiers and regular hardware tiers are non-interchangeable. |
To create a new Domino endpoint hardware tier:
-
From the admin home page, go to Advanced > Hardware Tiers.
-
Click New to create a hardware tier, or click Edit to modify an existing hardware tier or set a default hardware tier.
-
Select the desired hardware tier values, see Create hardware tier.
-
Select Is Domino endpoint Tier.
-
You can also specify if you’d like this Domino endpoint tier to be the default for all Domino endpoints.
To scale all Python Domino endpoints, set the degree of parallelism.
|
Note
| Only synchronous models support this. |
-
Go to Admin > Platform settings > Configuration records.
-
Set
com.cerebro.domino.modelmanager.uWsgi.workerCountto a value greater than its default value of1to increase the uWSGI worker count. See the uWSGI documentation for more information. -
The system shows the following message:
Changes here do not take effect until services are restarted. Click here to restart services. -
Click here to restart the services.
Learn more about Domino hardware tiers.