Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add feature flags to CR to specify payload configuration #165

Open
ruivieira opened this issue Nov 29, 2023 · 0 comments · May be fixed by #166
Open

Add feature flags to CR to specify payload configuration #165

ruivieira opened this issue Nov 29, 2023 · 0 comments · May be fixed by #166
Assignees
Labels
kind/enhancement New feature or request rhoai-2.6

Comments

@ruivieira
Copy link
Member

ruivieira commented Nov 29, 2023

As a user, I want to be able to specify whether a deployed TrustyAIService should configure a specific model server (e.g. ModelMesh or KServe) or not.

The operator should provide defaults if this configuration is not present.

As an example, if I do not want KServe inference services to be automatically configured, but ModelMesh ones to be, I would add the following to a TrustyAIService CR:

payloadProcessor:
   modelmesh: yes
   kserve: no

Validation

When deploying a TrustyAIService with

payloadProcessor:
   modelmesh: yes
   kserve: no

and a ModelMesh inference service: ModelMesh should be configured.

When deploying a TrustyAIService with

payloadProcessor:
   modelmesh: no
   kserve: yes

with ModelMesh inference service: ModelMesh should be not configured. With a KServe inference service: it should be configured.

When deploying a TrustyAIService with

payloadProcessor:
   modelmesh: yes
   kserve: yes

Any inference service (ModelMesh or KServe) should be configured.

@ruivieira ruivieira added kind/enhancement New feature or request rhoai-2.6 labels Nov 29, 2023
@ruivieira ruivieira self-assigned this Nov 29, 2023
@ruivieira ruivieira linked a pull request Nov 29, 2023 that will close this issue
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
kind/enhancement New feature or request rhoai-2.6
Projects
Status: Todo
Development

Successfully merging a pull request may close this issue.

1 participant