Fix model unload in server stop method

[sivanantha321]

What this PR does / why we need it:
Fixes model unload in model server stop method

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 #

Type of changes
Please delete options that are not relevant.

• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds functionality)
• Breaking change (fix or feature that would cause existing functionality to not work as expected)
• This change requires a documentation update

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

• Test B

• 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?
• Have you made corresponding changes to the documentation?

Release note:

[spolti]

Hi @sivanantha321, is there a issue or something that describes the problem or adds a background to it?
In this case, any loaded model remains there indefinitely?

[sivanantha321]

Hi @sivanantha321, is there a issue or something that describes the problem or adds a background to it? In this case, any loaded model remains there indefinitely?

There isn't a issue for this. In the code model.unload() is called but model does not have unload method. I just fixed that and regarding your question about model remaining in memory, I haven't tested that. But I believe that is not the case.

[spolti]

Hi @sivanantha321, is there a issue or something that describes the problem or adds a background to it? In this case, any loaded model remains there indefinitely?

There isn't a issue for this. In the code model.unload() is called but model does not have unload method. I just fixed that and regarding your question about model remaining in memory, I haven't tested that. But I believe that is not the case.

I see, thanks.

/lgtm

[yuzisun]

if get_models() is returning a map then you only need to do following, as the iterator loop through keys by default

for model_name in self.registered_models.get_models():
    self.registered_models.unload(model_name)

[sivanantha321]

Python does not allows modifying the dict while iterating, otherwise we will get a runtime error. For example,

Traceback (most recent call last):
  File "main.py", line 11, in <module>
    for model in map:
RuntimeError: dictionary changed size during iteration

[yuzisun]

/approve

[terrytangyuan]

/lgtm

[oss-prow-bot]

[APPROVALNOTIFIER] This PR is APPROVED

This pull-request has been approved by: sivanantha321, spolti, terrytangyuan, yuzisun

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:

• python/kserve/OWNERS [yuzisun]

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