[FA / tests] Add use_cache tests for FA models
#26415
Merged
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 documentation is not available anymore as the PR was closed or merged. |
LysandreJik
approved these changes
Sep 27, 2023
Member
LysandreJik
left a comment
LysandreJik
left a comment
There was a problem hiding this comment.
LGTM, thanks for your PR @younesbelkada!
5 tasks
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 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Outdated suggestions cannot be applied.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?
While testing out #26414 I realised the current tests silently pass as we only check for the immediate next predicted token
For small models FA2 is quite flaky so I have decided to not increase
max_new_tokensintest_flash_attn_2_generate_padding_rightandtest_flash_attn_2_generate_left_paddingand rather have a separate test that will rungeneratewithuse_cachewith a relatively largemax_new_tokensto catch issues with caching when porting models to FAcc @LysandreJik