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.

Sign up for GitHub

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

Jump to bottom

Using genai_config.json to configure dml options #23247

Open
manoj-jain-techporch opened this issue Jan 3, 2025 · 2 comments
Open

Using genai_config.json to configure dml options #23247

manoj-jain-techporch opened this issue Jan 3, 2025 · 2 comments
Labels
ep:DML issues related to the DirectML execution provider

Comments

@manoj-jain-techporch
Copy link

a) What options can one list under "provider_options"-"dml" in genai_config.json?
b) Specifically, how can one select NPU or GPU to load the model based on options listed under "provider_options"-"dml"?

Can't find any documentation that list all possible values under this section in the JSON file.
@github-actions github-actions bot added the ep:DML issues related to the DirectML execution provider label Jan 3, 2025
@yuslepukhin
Copy link
Member

This issue should probably be file with GenAI

@manoj-jain-techporch
Copy link
Author

Hi Dimitry - Thanks for the response. But since genai_config.json is a tool in ONNXRuntime, shouldn't there be some documentation on what all flags/options a user can specify in this file that will be passed on to DML? Name and valid values for each such option?

Also, how should I file this issue with GenAI? Where?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
ep:DML issues related to the DirectML execution provider
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@yuslepukhin @manoj-jain-techporch