microsoft / onnxruntime

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
https://onnxruntime.ai
MIT License
13.93k stars 2.81k forks source link

[VitisAI] Wrong model path after using std::filesystem::path #21279

Open BoarQing opened 1 month ago

BoarQing commented 1 month ago

Describe the issue

after https://github.com/microsoft/onnxruntime/pullafter /20920, the onnxruntime with provider option --use-vitisai can't be compiled. In addition, It is using the model path instead of path we specified(l(usually an intermediate model during graph transformation for debugging).

We highly recommended that the onnxruntime's CI can be tested with --use-vitisai, at least for compile.

To reproduce

No need to reproduce.

Urgency

No response

Platform

Windows

OS Version

Win 11

ONNX Runtime Installation

Built from Source

ONNX Runtime Version or Commit ID

main

ONNX Runtime API

C++

Architecture

X64

Execution Provider

Vitis AI

Execution Provider Library Version

No response

BoarQing commented 1 month ago

@snnn

BoarQing commented 1 month ago

Sample compile error: image

snnn commented 1 month ago

Should have been fixed by #21247

BoarQing commented 1 month ago

Should have been fixed by #21247 No. This only solves the compile issue

BoarQing commented 1 month ago

Should have been fixed by #21247

https://github.com/microsoft/onnxruntime/pull/21293 Could you review this PR that address the issue mentioned on the title.

github-actions[bot] commented 2 weeks ago

This issue has been automatically marked as stale due to inactivity and will be closed in 30 days if no further activity occurs. If further support is needed, please provide an update and/or more details.