Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

update min dtype in falcon for prevent bf16 execution issue #1093

Merged

Conversation

eaidova
Copy link
Collaborator

@eaidova eaidova commented Dec 23, 2024

What does this PR do?

in 4.45 when _prepare_4d_causal_attention_mask_with_cache_position was function, it had argument for passing min_dtype, in 4.46 it was excluded, this PR updates patching for resolving bf16 execution issues

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?

@eaidova eaidova added the openvino-test Trigger OpenVINO slow tests label Dec 23, 2024
@HuggingFaceDocBuilderDev

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.

@eaidova
Copy link
Collaborator Author

eaidova commented Dec 23, 2024

nightly tests failure is not related, it is caused by openvino python API unexpected changes

Copy link
Collaborator

@echarlaix echarlaix left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks for the fix @eaidova !

optimum/exporters/openvino/model_patcher.py Outdated Show resolved Hide resolved
@echarlaix echarlaix merged commit 48e72ef into huggingface:main Dec 25, 2024
23 of 28 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
openvino-test Trigger OpenVINO slow tests
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants