generation utils update (minor) #1468
Open
+34
−30
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
- Fix the type hint, dtype can not be a str - Fix the device hint - Remove the pad token id arg, the decoder_attention_mask is a binary of 0, and 1
- Added an early return - Extracted is_mqa_model and lazy_mode to avoid repeated dictionary lookups - Used more descriptive variable names and simplified the nested loops for better readability
yafshar
requested review from
ssarkar2,
bhargaveede and
vivekgoe
as code owners
|
The text-generation CI has been executed and will be compared with the main branch once the run is complete. |
There was a problem hiding this comment.
@yafshar , Just a couple of comments below.
Please post results of CI, before and after change.
|
@yafshar , Makes sense. |
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Outdated suggestions cannot be applied.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?
transformers.streamers->transformers.generation.streamersreturn x.index_fill(1, torch.tensor(0), 1)uses the wrong index oftorch.tensor(0), it is fixed to the correct index on the correct deviceindex = torch.tensor(0, device=device)Before submitting