Fix seq_len for padding sequences #318
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
madamczykhabana
requested review from
kzawora-intel,
iboiko-habana and
michalkuligowski
michalkuligowski
approved these changes
Sep 23, 2024
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Outdated suggestions cannot be applied.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.
Before the fix we used seq_len=0 for padding samples. This was later translated to an empty attention_mask (since we don't have any tokens that we should include in calculations) and in turn caused NaNs in prompt attention (0 divided by 0). Those NaNs later got propagated to kv-cache causing issues in flat_pa.