[v0.11.1] Increase memory limit of kserve-controller pod

[israel-hdez]

What this PR does / why we need it:

The increased memory limit is for the controller pod to work normally in clusters having 9k+ secrets.

Which issue(s) this PR fixes

Fixes https://issues.redhat.com/browse/RHOAIENG-3996

Type of changes
Please delete options that are not relevant.

• Bug fix (non-breaking change which fixes an issue)

Feature/Issue validation/testing:

With KServe deployed:

• Use a script from @skonto available in this gist: https://gist.github.com/skonto/188b2c45c5af449629caaa69a190392c, with a minor modification: edit line 3 to NC=64
• Try to deploy an InferenceService (any ISVC simple should work).
  • Without the patch, observe an OOMKill.
  • With the patch, the pod should not die.

[openshift-ci]

[APPROVALNOTIFIER] This PR is APPROVED

This pull-request has been approved by: israel-hdez

The full list of commands accepted by this bot can be found here.

The pull request process is described here

Needs approval from an approver in each of these files:

• OWNERS [israel-hdez]

Approvers can indicate their approval by writing /approve in a comment
Approvers can cancel approval by writing /approve cancel in a comment

[terrytangyuan]

Should we make this change to master branch first and then cherry-pick to the release branch?

[israel-hdez]

Should we make this change to master branch first and then cherry-pick to the release branch?

We could, although I'm not sure if it would be short-lived if the upstream fix is merged soon.
The master branch would get the long-term fix is if the upstream PR is approved.

If you prefer the fix to be in master too, I could cherry-pick this to master (commits are going to be different, anyway).

[terrytangyuan]

/lgtm