Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Added QNN EP for ARM64 builds. #41

Merged
merged 15 commits into from
Dec 13, 2024
Merged

Added QNN EP for ARM64 builds. #41

merged 15 commits into from
Dec 13, 2024

Conversation

azchohfi
Copy link
Contributor

No description provided.

@azchohfi
Copy link
Contributor Author

Not ready for review since the exported projects are not great yet... I'm not sure what to do there...

@nmetulev nmetulev changed the base branch from main to dev/npu December 13, 2024 14:29
@nmetulev
Copy link
Member

@azchohfi, I made few changes to address my initial comments, please take a look.

In addition, the exported projects still need work to include ORT.QNN instead of ORT.DML. Also, the execution provider in the exported project defaults to CPU even if NPU is selected in the app. Once this is added, I would be good to merge this in

@azchohfi azchohfi marked this pull request as ready for review December 13, 2024 18:43
@azchohfi
Copy link
Contributor Author

Not sure why the build is not showing up as executed here. It is passing.

Copy link
Contributor

@zateutsch zateutsch left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Approved with one minor comment.

Comment on lines +48 to +58
else if (hardwareAccelerator == HardwareAccelerator.QNN)
{
Dictionary<string, string> options = new()
{
{ "backend_path", "QnnHtp.dll" },
{ "htp_performance_mode", "high_performance" },
{ "htp_graph_finalization_optimization_mode", "3" }
};
_sessionOptions.AppendExecutionProvider("QNN", options);
_chunkSize = 8;
}
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Should be removed if we're not doing NPU for all-Mini

@nmetulev nmetulev enabled auto-merge December 13, 2024 20:15
@nmetulev nmetulev merged commit 012dd7f into dev/npu Dec 13, 2024
3 checks passed
@nmetulev nmetulev deleted the alzollin/qnn branch December 13, 2024 21:23
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants