-
Notifications
You must be signed in to change notification settings - Fork 2.8k
docs: adr for model and stages redesign #2114
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
base: main
Are you sure you want to change the base?
Conversation
Signed-off-by: Michele Dolfi <[email protected]>
✅ DCO Check Passed Thanks @dolfim-ibm, all your commits are properly signed off. 🎉 |
Merge ProtectionsYour pull request matches the following merge protections and will not be merged until they are valid. 🟢 Enforce conventional commitWonderful, this rule succeeded.Make sure that we follow https://www.conventionalcommits.org/en/v1.0.0/
|
Codecov Report✅ All modified and coverable lines are covered by tests. 📢 Thoughts on this report? Let us know! |
|
||
Model runtimes are as generic as possible (but very likely some duplicates might still be there). | ||
|
||
1. they operate only on basic objects like PIL images and only expose API for batch predictions |
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.
maybe also PIL + chat-template (!= prompt)
4. model runtime could still have some intenal pre-/post-processing, but it should be limited to model internals, e.g. normalization of images to RGB. | ||
|
||
Open questions: | ||
a. should __init__ load the models or we prefer lazy loading? |
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.
I would prefer a lazy option with a force download option.
This is a discussion thread on the idea of redesigning the model runtimes and stages.