kevinintel

Thanks for reporting it, we will check the issue

It looks like load/save mismatch, can you try to use latest commit instead of g494a5712fa2 and set use_neural_speed=False?

Thanks for reporting it, we will check the issue

Hi @kithogue , can you share your use case?

Close it first until the user provide details

We already support onnx, please refer to: https://github.com/intel/intel-extension-for-transformers/blob/main/intel_extension_for_transformers/llm/runtime/deprecated/docs/deploy_and_integration.md

if you don't have other questions, i will close this issue.

Hi bmtuan, can you use the example?

I will close this issue if you don't have concerns

Thank to your feedback, we will support it.