Regarding the ONNX model acceleration on Kria KV260

[sandyagur8]

Hey there i have been trying to quantize and run the ONNX model using Vitis-AI 3.5 . I have tried previous versions also but they all propose a on the go quantisation.
so long story short i compiled the onnx model using vai_q_onnx quantisation completed and i got the quantized onnx model. But how can i run this on my KV260 board? Is there a way to convert this onnx to xmodel? or running it using VitisAIExecutionProvider is the only way?

BTW the execution provider method is causing a lot of pain and errors mainly due to version incompatabilities .
Any help regarding this is appreciated
Regards