Do not drop mask with SDPA for more cases#30311
Merged
Conversation
|
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. |
ArthurZucker
approved these changes
Apr 18, 2024
Collaborator
ArthurZucker
left a comment
There was a problem hiding this comment.
Fine, but the code is too verbose, while being super hard to understand.
There are 2 possible outcomes. Either we ignore or not.
Returning the value earlier here would help tremendously.
Could you pin point which part was not taken into account for speculative decoding? qlen==1 + qlen == klen?
Contributor
Author
|
@ArthurZucker will be cleaner once #30070 is brought back |
Collaborator
|
I 'll be harsher to make it clearer! |
ydshieh
pushed a commit
that referenced
this pull request
Apr 23, 2024
* overlooked * style * cleaner
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
As per title. Overlooked in #30127 (issue with speculative decoding, where no attn_mask is passed to the main model).