[WIP] Add flex attention for gpt2 #34861
Draft
+2
−224
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
|
cc @ArthurZucker for review, but in the meantime @mayankagarwals you can make the tests pass by doing |
|
Thanks a ton, got it. Waiting for discussions to close here #34896. Thinking that PR should follow similar guidelines to keep one standard design of implementation of generic attention block. @vasqu Let me know once major design bits are closed! I'm following your PR for gpt neox and aligned with everything there. |
|
@mayankagarwals Sure I'll let you know when stuff clears up! |
|
Having a look at your PR @vasqu, I think quite a few things were fixed since so will check! |
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Outdated suggestions cannot be applied.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.
What does this PR do?
Adding flex_attention for Gpt2 model following #34809
Who can review?