[HybridCache] disable automatic compilation#36620
Merged
gante merged 2 commits intohuggingface:mainfrom Mar 10, 2025
Merged
Conversation
Contributor
|
Hi 👋, thank you for opening this pull request! The pull request is converted to draft by default. When it is ready for review, please click the |
c21f46f to
a75a906
Compare
gante
commented
Mar 9, 2025
| ⚠️ Runs two sequential generations to ensure the cache doesn't get stuck after the first compiled run! ⚠️ | ||
| """ | ||
| # Monkey-patching the HybridCache at test-time to continue testing compilation support | ||
| HybridCache.is_compileable = True |
Contributor
Author
There was a problem hiding this comment.
(CI also fails without this change :) we would need to rewrite the test)
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
Collaborator
ArthurZucker
left a comment
There was a problem hiding this comment.
thanks and indeed better to disable while we don't know what's happening!
ArthurZucker
approved these changes
Mar 10, 2025
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What does this PR do?
Recently I've expanded auto compilation in
generatefromStaticCacheonly to all compilable caches, through a newis_compileableattribute.This PR sets
HybridCache.is_compileabletoFalse, which stops automatic compilation. There have been reports of speed loss on models that use this cache -- disabling until the root cause is found.