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

Conversion will be much slower on Python 3.9.6 #289

Closed
TimYao18 opened this issue Oct 26, 2023 · 3 comments
Closed

Conversion will be much slower on Python 3.9.6 #289

TimYao18 opened this issue Oct 26, 2023 · 3 comments

Comments

@TimYao18
Copy link

After benchmarking M1, M2, and M2 Pro, I found that the conversion on Python 3.9.6 is much slower compared to Python 3.11.5.

On M1, the conversion of RealVisXL 2.0 takes 14XXX seconds on Python 3.9.6, while it only takes 7XXX seconds on Python 3.11.5.
It is approximately twice as slow as on Python 3.11.5.

Is there someone know why? After checking the change notes of Python I didn't found the reason.

@czkoko
Copy link

czkoko commented Oct 26, 2023

The speed is not normal. If there is no quantitative model, the time should be less than half an hour.

@TimYao18
Copy link
Author

Is conversion time so short?
I test M2 Pro on XL based model will still take more than 1.5 hours on Python 3.11.5.

@TimYao18
Copy link
Author

3.11 is average of 25%faster than 3.10.
https://docs.python.org/3/whatsnew/3.11.html#faster-cpython

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

No branches or pull requests

2 participants