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

[Documentation] ORT Format Model Version Table Needs Update #20670

Open
RyanRio opened this issue May 13, 2024 · 2 comments
Open

[Documentation] ORT Format Model Version Table Needs Update #20670

RyanRio opened this issue May 13, 2024 · 2 comments
Assignees
Labels
documentation improvements or additions to documentation; typically submitted using template

Comments

@RyanRio
Copy link

RyanRio commented May 13, 2024

Describe the documentation issue

The documentation for the ORT model format version support -

image

needs an update (for v6 support) for the latest ONNX runtime versions. From my testing v6 isn't supported by 1.15.1, is the only way to convert to an earlier version to downgrade the python conversion tool to an earlier version? There's no argument there, so that process could be useful documentation as well.

Page / URL

https://onnxruntime.ai/docs/performance/model-optimizations/ort-format-models.html

@RyanRio RyanRio added the documentation improvements or additions to documentation; typically submitted using template label May 13, 2024
@RyanRio
Copy link
Author

RyanRio commented May 13, 2024

Actually, for is the only way to convert to an earlier version to downgrade the python conversion tool to an earlier version I think this covers it -

If you are building ONNX Runtime from source (custom, reduced or minimal builds), you must match the python package version to the branch of the ONNX Runtime repository you checked out.

@edgchen1
Copy link
Contributor

We don't generally support forwards compatibility. v6 was introduced in ORT 1.16.0 so the minimum version you would be able to use a v6 model in is 1.16.0.

@sophies927 sophies927 self-assigned this May 15, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
documentation improvements or additions to documentation; typically submitted using template
Projects
None yet
Development

No branches or pull requests

3 participants