-
Notifications
You must be signed in to change notification settings - Fork 862
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
[tabular] mention persist and compile in deploy tutorial #2717
Conversation
Job PR-2717-a175686 is done. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Added some comments, looks good overall!
```{.python .input} | ||
predictor_clone_opt.compile_models() | ||
``` |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This will probably cause the tutorial to return False in the later check that the predictions are equivalent. Instead, have the equivalency checks prior to the compile_models step, then predict again and mention that predictions might not be exactly the same, but should be very close.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Moved to bottom part of the tutorial and mentioned the potential difference.
Job PR-2717-0298008 is done. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Looks great! Had 1 comment
Job PR-2717-64c6a22 is done. |
Issue #, if available:
Description of changes:
This PR updates the tabular model deployment tutorial with some context on
persist_models
andcompile_models
for efficient real-time prediction.By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.