How to Use Neutron Execution Provider with ONNXRT?

[NXP_imx93evk_user]

Hello

While reading the GEN-AI-RAG-WHITEPAPER.pdf provided by NXP, I found that the TinyLlama-1B quantized model was ported to the i.MX95 device using the Neutron Execution Provider within ONNXRT runtime.

I have a few questions regarding this:

1. Does ONNXRT refer to onnxruntime?
2. I would like to try using the Neutron Execution Provider with ONNXRT as well. Could you provide guidance on how to set up the environment for this?Additionally, how can I apply it in the code?

A detailed explanation would be greatly appreciated. Thank you in advance for your support!

[Zhiming_Liu]

Hello,

There is no public information available to explain this process, so please wait for the eIQ tool and BSP to be officially released.

Best Regards,
Zhiming