Support Gemma3 models

[LarryatIntel]

Looks like Gemma3 models used new transformer, and optimum-cli has not supported it now, when can optimum-cli can support Gemma3?

(ov_llm) C:\Users\Local_Admin\models\Qwentest>optimum-cli export openvino -m google/gemma-3-1b-it --weight-format int4 --sym --group-size 128 --ratio 1.0 google/gemma-3-1b-it
:207: DeprecationWarning: The openvino.runtime module is deprecated and will be removed in the 2026.0 release. Please replace openvino.runtime with openvino.
Traceback (most recent call last):
File "", line 198, in run_module_as_main
File "", line 88, in run_code
File "C:\ProgramData\miniforge3\envs\ov_llm\Scripts\optimum-cli.exe_main.py", line 7, in
File "C:\ProgramData\miniforge3\envs\ov_llm\Lib\site-packages\optimum\commands\optimum_cli.py", line 208, in main
service.run()
File "C:\ProgramData\miniforge3\envs\ov_llm\Lib\site-packages\optimum\commands\export\openvino.py", line 466, in run
main_export(
File "C:\ProgramData\miniforge3\envs\ov_llm\Lib\site-packages\optimum\exporters\openvino_main.py", line 267, in main_export
raise ValueError(
ValueError: Trying to export a gemma3-text model, that is a custom or unsupported architecture, but no custom export configuration was passed as custom_export_configs. Please refer to https://huggingface.co/docs/optimum/main/en/exporters/onnx/usage_guides/export_a_model#custom-export-of-transformers-models for an example on how to export custom models. Please open an issue at https://github.com/huggingface/optimum-intel/issues if you would like the model type gemma3-text to be supported natively in the OpenVINO export.