fix: correct attention mask padding amount in prepare_attention_mask#596
Open
Mr-Neutr0n wants to merge 1 commit into
Open
fix: correct attention mask padding amount in prepare_attention_mask#596Mr-Neutr0n wants to merge 1 commit into
Mr-Neutr0n wants to merge 1 commit into
Conversation
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Fix incorrect
F.padcall inAttention.prepare_attention_mask()(opensora/models/diffusion/opensora_v1_3/modules.py).F.pad(tensor, (0, N))pads byNelements on the right — it does not pad to a total length ofN. The existing code uses(0, target_length), which produces a tensor of lengthcurrent_length + target_lengthinstead oftarget_length.Before
After
This ensures the mask is padded to exactly
target_lengthelements, as intended.