Skip to content

Sasarkar/437 llama#671

Merged
regisss merged 13 commits into
transformers_4.35from
sasarkar/437_llama
Jan 30, 2024
Merged

Sasarkar/437 llama#671
regisss merged 13 commits into
transformers_4.35from
sasarkar/437_llama

Conversation

@regisss
Copy link
Copy Markdown
Collaborator

@regisss regisss commented Jan 30, 2024

What does this PR do?

Fixes # (issue)

Before submitting

  • This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
  • Did you make sure to update the documentation with your changes?
  • Did you write any new necessary tests?

@regisss regisss requested a review from a user January 30, 2024 22:04
@regisss regisss requested a review from ZhaiFeiyue as a code owner January 30, 2024 22:04
@regisss regisss merged commit e59e9d8 into transformers_4.35 Jan 30, 2024
@regisss
Copy link
Copy Markdown
Collaborator Author

regisss commented Feb 5, 2024

@ssarkar2 Can you let me know the changes you applied to modeling_attn_mask_utils.py? It will be easier to review

@ssarkar2
Copy link
Copy Markdown
Contributor

ssarkar2 commented Feb 5, 2024

For this file some changes made were:

cast removal
ba81579
@MohitIntel saw an error without this change, he might have more details

remove "all" check:
elif not is_tracing:# and torch.all(attention_mask == 1):
This was done for speed up

gplutop7 pushed a commit to HabanaAI/optimum-habana-fork that referenced this pull request Oct 15, 2025
…gface#2251) (huggingface#671)

Signed-off-by: Daniel Socek <daniel.socek@intel.com>
Co-authored-by: Daniel Socek <daniel.socek@intel.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants