Fixing flex attention for torch=2.6.0#37285
Merged
ArthurZucker merged 6 commits intohuggingface:mainfrom Apr 7, 2025
Merged
Conversation
Contributor
|
Hi 👋, thank you for opening this pull request! The pull request is converted to draft by default. The CI will be paused while the PR is in draft mode. When it is ready for review, please click the |
vasqu
reviewed
Apr 4, 2025
| if self._is_flex_compiled is False: | ||
| self._compiled_flex_attention = torch.compile(flex_attention, dynamic=False) | ||
| if not self._is_flex_compiled: | ||
| if _torch_version == "2.6.0": |
Contributor
There was a problem hiding this comment.
Could you add a comment here to describe why this is the case, e.g. by linking to the issue with a small description?
Might be also nice to use/create something like
Collaborator
There was a problem hiding this comment.
I tested on my end this should fix training!
Contributor
|
Seems like the llama4 addition changed flex compilation #37307 😄 |
Collaborator
|
Flex was not working for decoding! |
ArthurZucker
approved these changes
Apr 7, 2025
| if self._is_flex_compiled is False: | ||
| self._compiled_flex_attention = torch.compile(flex_attention, dynamic=False) | ||
| if not self._is_flex_compiled: | ||
| if _torch_version == "2.6.0": |
Collaborator
There was a problem hiding this comment.
I tested on my end this should fix training!
ArthurZucker
added a commit
that referenced
this pull request
Apr 7, 2025
* adding compile kwarg for torch 2.6 * fixing dynamic * addressing comment * typo * Update src/transformers/integrations/flex_attention.py --------- Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>
cyr0930
pushed a commit
to cyr0930/transformers
that referenced
this pull request
Apr 18, 2025
* adding compile kwarg for torch 2.6 * fixing dynamic * addressing comment * typo * Update src/transformers/integrations/flex_attention.py --------- Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>
zucchini-nlp
pushed a commit
to zucchini-nlp/transformers
that referenced
this pull request
May 14, 2025
* adding compile kwarg for torch 2.6 * fixing dynamic * addressing comment * typo * Update src/transformers/integrations/flex_attention.py --------- Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>
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
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?
This PR fixes this issue originally raised in pytorch core pytorch/pytorch#146260 for flex attention on 2.6.0, by setting
mode="max-autotune-no-cudagraphs".Fixes # (issue)
Before submitting
Pull Request section?
to it if that's the case.
documentation guidelines, and
here are tips on formatting docstrings.
Who can review?
@ArthurZucker