Remove flakiness in VLMs #36242
Merged
Remove flakiness in VLMs #36242
Conversation
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
|
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. |
Contributor
|
Thank you for fixing @zucchini-nlp 🤗 |
zucchini-nlp
added a commit
to zucchini-nlp/transformers
that referenced
this pull request
Feb 21, 2025
* fix * nit * no logits processor needed * two more tests on assisted decoding
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Outdated suggestions cannot be applied.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?
As per title. Only one test was flaky for VLMs -
test_promp_loopup_decoding. Unfortunately it can't be fixed by suppressing image/video tokens because the Prompt Lookup doesn't apply any logits processor. This can be fixed with some additional effort, but not worth it. VLMs don't use these type of assisted decoding usually, haven't seen any issues from the community