c# I need to run the program on NPU (OnnxRuntime + DirectML + NPU)，

[Gusha-nye]

Hello, big guys, I checked the Microsoft blog and did the following test(https://blogs.windows.com/windowsdeveloper/2024/02/01/introducing-neural-processor-unit-npu-support-in-directml-developer-preview/)

Following the demo of Microsoft（https://github.com/microsoft/Phi3-Chat-WinUI3-Sample）, I can run phi3 model on GPU via Onnxruntime + DirectML. By using C#, I want to run program on NPU (OnnxRuntime + DirectML + NPU), but it failed.
I already install Microsoft.AI.DirectML 1.13.1 and the Microsoft.ML.Onnxruntime.DirectML 1.17.1 on VS 2022 Nuget
And I write C# test code in demo, as follows:

And when '4> Index >= 0' output with [DmlExecutionProvider, CPUExecutionProvider]

When I set 'Index=4', the error is occured as follows:

when 'Index >= 5', the error is occured as follows:

However, in the Microsoft demo, the loading of the phi3 model is also not configured using similar code as below
SessionOptions options = new SessionOptions();
options.AppendExecutionProvider_DML(Index)

Therefore, how can the reasoning of phi3 be executed on the NPU?
Is there currently a demo that can reason about Phi3 via OnnxRuntime + DirectML on NPU? (C#, C++, python are all good)

My PC configuration as follows:
Processor: Intel(R) Core(TM) Ultra 7 165H 1.40GHz
GPU: Intel(R) Arc(TM) Graphics
NPU: Intel(R) AI Boost
Installed RAM: 32.0GB
System Type:64-bit operating system, x64-based processor
Windows Edition: Windows 11 pro
version: 24H2