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.