What this PR does / why we need it:

Context: Updating vllm in nixpkgs (NixOS/nixpkgs#467418).

EDIT: Updated to fix compatibility with vllm 0.15.0.

Latest vllm release 0.12.0 changed the location of a few classes (Embedding* and Rerank*).
This PR updates the imports in kserve/protocol/rest/openai/types/__init__.py.

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:

Before, this PR, running kserve's test suite had a few failures:

=========================== short test summary info ============================
ERROR test/test_dataplane.py
ERROR test/test_model_repository.py
ERROR test/test_openai_completion.py
ERROR test/test_openai_encoder.py
================= 173 passed, 131 warnings, 4 errors in 32.00s =================

Example:

_________________ ERROR collecting test/test_openai_encoder.py _________________
ImportError while importing test module '/build/source/python/kserve/test/test_openai_encoder.py'.
Hint: make sure your test modules/packages have valid Python names.
Traceback:
/nix/store/3lll9y925zz9393sa59h653xik66srjb-python3-3.13.9/lib/python3.13/importlib/__init__.py:88: in import_module
    return _bootstrap._gcd_import(name[level:], package, level)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
test/test_openai_encoder.py:20: in <module>
    from kserve.protocol.rest.openai import (
kserve/protocol/rest/openai/__init__.py:16: in <module>
    from .openai_model import (
kserve/protocol/rest/openai/openai_model.py:22: in <module>
    from kserve.protocol.rest.openai.types import (
kserve/protocol/rest/openai/types/__init__.py:35: in <module>
    from vllm.entrypoints.pooling.embed.protocol import RerankRequest, RerankResponse as Rerank
E   ImportError: cannot import name 'RerankRequest' from 'vllm.entrypoints.pooling.embed.protocol'

After this change, all tests are successful.

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:

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.