Disable default sdpa in Albert (#22) #1517
Merged
Conversation
This file contains 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
|
Hi @libinta this commit is also required with next OH release |
jiminha
changed the title
jiminha
approved these changes
Nov 25, 2024
|
The code quality check failed, please run |
|
@astachowiczhabana Please rebase your branch on main and run make style to make the code quality check pass |
|
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. |
Transformers v4.45 introduced sdpa as the default implementation in Albet. This caused performance drop. Adding Albert to the list of models which don't yet have sdpa implementation in Gaudi and use thus eager attention.
astachowiczhabana
force-pushed
the
auto-pr-265931a
branch
from
66897cd to
ef54499
Compare
|
change rebased |
MohitIntel
pushed a commit
that referenced
this pull request
Nov 26, 2024
Co-authored-by: Urszula Golowicz <[email protected]>
Liangyx2
pushed a commit
to HabanaAI/optimum-habana-fork
that referenced
this pull request
Jan 20, 2025
Co-authored-by: Urszula Golowicz <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
Transformers v4.45 introduced sdpa as the default implementation in Albet. This caused performance drop.
Adding Albert to the list of models which don't yet have sdpa implementation in Gaudi and use thus eager attention.