optimum[openvino] 2.1.0 breaks compatibility with AITK olive-recipes

[mkruszyx]

Related to PR #2339 9f32828

Updated version of optimum[openvino] breaks compatibility with AITK olive-recipes.

Olive-recipes have optimum[openvino] version locked on 1.26.1 which is no longer compatible with current state of Olive main stream.

Recipes need to be updated or Olive needs to support both versions.

Traceback (most recent call last):
  File "/home/jenkins/agent/workspace/DL-Benchmark/prod/download/WW09.1-download-129/msft_convert_olive/venv_phi-4_GPU/lib/python3.12/site-packages/olive/passes/openvino/optimum_intel.py", line 353, in _run_for_config
    from optimum.intel.openvino.configuration import (
ImportError: cannot import name '_GPTOSSQuantizationConfig' from 'optimum.intel.openvino.configuration' (/home/jenkins/agent/workspace/DL-Benchmark/prod/download/WW09.1-download-129/msft_convert_olive/venv_phi-4_GPU/lib/python3.12/site-packages/optimum/intel/openvino/configuration.py). Did you mean: 'OVQuantizationConfig'?

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
  File "/home/jenkins/agent/workspace/DL-Benchmark/prod/download/WW09.1-download-129/msft_convert_olive/venv_phi-4_GPU/bin/olive", line 10, in <module>
    sys.exit(main())
             ^^^^^^
  File "/home/jenkins/agent/workspace/DL-Benchmark/prod/download/WW09.1-download-129/msft_convert_olive/venv_phi-4_GPU/lib/python3.12/site-packages/olive/cli/launcher.py", line 70, in main
    service.run()
  File "/home/jenkins/agent/workspace/DL-Benchmark/prod/download/WW09.1-download-129/msft_convert_olive/venv_phi-4_GPU/lib/python3.12/site-packages/olive/cli/run.py", line 62, in run
    workflow_output = olive_run(
                      ^^^^^^^^^^
  File "/home/jenkins/agent/workspace/DL-Benchmark/prod/download/WW09.1-download-129/msft_convert_olive/venv_phi-4_GPU/lib/python3.12/site-packages/olive/workflows/run/run.py", line 178, in run
    return run_engine(package_config, run_config)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/jenkins/agent/workspace/DL-Benchmark/prod/download/WW09.1-download-129/msft_convert_olive/venv_phi-4_GPU/lib/python3.12/site-packages/olive/workflows/run/run.py", line 139, in run_engine
    return engine.run(
           ^^^^^^^^^^^
  File "/home/jenkins/agent/workspace/DL-Benchmark/prod/download/WW09.1-download-129/msft_convert_olive/venv_phi-4_GPU/lib/python3.12/site-packages/olive/engine/engine.py", line 208, in run
    self.run_accelerator(
  File "/home/jenkins/agent/workspace/DL-Benchmark/prod/download/WW09.1-download-129/msft_convert_olive/venv_phi-4_GPU/lib/python3.12/site-packages/olive/engine/engine.py", line 285, in run_accelerator
    self._run_no_search(input_model_config, input_model_id, accelerator_spec, artifacts_dir)
  File "/home/jenkins/agent/workspace/DL-Benchmark/prod/download/WW09.1-download-129/msft_convert_olive/venv_phi-4_GPU/lib/python3.12/site-packages/olive/engine/engine.py", line 329, in _run_no_search
    should_prune, signal, model_ids = self._run_passes(input_model_config, input_model_id, accelerator_spec)
                                      ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/jenkins/agent/workspace/DL-Benchmark/prod/download/WW09.1-download-129/msft_convert_olive/venv_phi-4_GPU/lib/python3.12/site-packages/olive/engine/engine.py", line 622, in _run_passes
    model_config, model_id = self._run_pass(
                             ^^^^^^^^^^^^^^^
  File "/home/jenkins/agent/workspace/DL-Benchmark/prod/download/WW09.1-download-129/msft_convert_olive/venv_phi-4_GPU/lib/python3.12/site-packages/olive/engine/engine.py", line 717, in _run_pass
    output_model_config = host.run_pass(p, input_model_config, output_model_path)
                          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/jenkins/agent/workspace/DL-Benchmark/prod/download/WW09.1-download-129/msft_convert_olive/venv_phi-4_GPU/lib/python3.12/site-packages/olive/systems/local.py", line 45, in run_pass
    output_model = the_pass.run(model, output_model_path)
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/jenkins/agent/workspace/DL-Benchmark/prod/download/WW09.1-download-129/msft_convert_olive/venv_phi-4_GPU/lib/python3.12/site-packages/olive/passes/olive_pass.py", line 243, in run
    output_model = self._run_for_config(model, self.config, output_model_path)
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/jenkins/agent/workspace/DL-Benchmark/prod/download/WW09.1-download-129/msft_convert_olive/venv_phi-4_GPU/lib/python3.12/site-packages/olive/passes/openvino/optimum_intel.py", line 360, in _run_for_config
    raise ImportError("Please install Intel® optimum[openvino] to use OpenVINO Optimum Conversion") from e
ImportError: Please install Intel® optimum[openvino] to use OpenVINO Optimum Conversion

[mkruszyx]

@Anirudh-Swaminathan