[RHOAIENG-19717] Pod now has correct imagepull secret when updated in raw deployment

[andresllh]

What this PR does / why we need it:
This issue was found while using Modelcars feature. For Modelcars, users may prefer using a private container registry to store their models. When using a private registry, it is required to provide a pull secret in the InferenceService so that the cluster can pull the model container.

At any time, and for any reason, users may require to replace/update the pull secret. This operation is done on the InferenceService. It is observed that when replacing the pull secret, the old one won't be removed in the updated deployment.
Which issue(s) this PR fixes (optional, in fixes #<issue number>(, fixes #<issue_number>, ...) format, will close the issue(s) when PR gets merged):
Fixes #
RHOAIENG-19717
Type of changes
Please delete options that are not relevant.

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

Feature/Issue validation/testing:

Please describe the tests that you ran to verify your changes and relevant result summary. Provide instructions so it can be reproduced.
Please also list any relevant details for your test configuration.

• Test A

1. Created the following Inference Service

apiVersion: serving.kserve.io/v1beta1
kind: InferenceService
metadata:
  name: sample-isvc-using-oci
  namespace: oci-model-example
  annotations:
    serving.kserve.io/deploymentMode: RawDeployment
spec:
  predictor:
    imagePullSecrets:
    - name: pull-secret-one
    model:
      runtime: vllm-runtime # This is the name of the ServingRuntime resource
      modelFormat:
        name: vLLM
      storageUri: oci://quay.io/rh-ee-allausas/huggingface:latest
      args:
        - --dtype=half
      resources:
        limits:
          nvidia.com/gpu: 1
        requests:
          nvidia.com/gpu: 1

2. Check the imagePullSecret from the pod that gets created
3. Edit the Inference Service and change the imagePullSecret
4. Check the imagePullSecret from the new pod that gets created and verify that it matches

• Logs

Special notes for your reviewer:

1. Please confirm that if this PR changes any image versions, then that's the sole change this PR makes.

Checklist:

• Have you added unit/e2e tests that prove your fix is effective or that this feature works?
• Has code been commented, particularly in hard-to-understand areas?

Release note:

Re-running failed tests

• /rerun-all - rerun all failed workflows.
• /rerun-workflow <workflow name> - rerun a specific failed workflow. Only one workflow name can be specified. Multiple /rerun-workflow commands are allowed per comment.

[openshift-ci]

Skipping CI for Draft Pull Request.
If you want CI signal for your change, please convert it to an actual PR.
You can still manually trigger a test run with /test all

[andresllh]

/cc @israel-hdez @spolti @brettmthompson

[israel-hdez]

/retest

[andresllh]

/retest

[andresllh]

/rerun-all

[openshift-ci]

[APPROVALNOTIFIER] This PR is APPROVED

This pull-request has been approved by: andresllh, brettmthompson

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 [andresllh,brettmthompson]

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