Skip to content

[CI][GHA] Enable GGUF Test on MacOS #2497

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.

Sign up for GitHub

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

Open
wants to merge 7 commits into
base: master
Choose a base branch
from
+0 −4
Open

[CI][GHA] Enable GGUF Test on MacOS #2497

Changes from 1 commit
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
fce45de
Re-enable gguf test on macos
Jul 29, 2025
09207bd
debug macos segment fault issue
Aug 1, 2025
02e73dc
debug only, increase gguf test timeout on macos
Aug 1, 2025
93567c1
Revert "debug only, increase gguf test timeout on macos"
Aug 7, 2025
f408f26
Revert "debug macos segment fault issue"
Aug 7, 2025
d085a61
Merge branch 'master' into enable_gguf_macos_test
Aug 7, 2025
02324f8
Merge branch 'master' into enable_gguf_macos_test
Aug 7, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 0 additions & 4 deletions tests/python_tests/test_gguf_reader.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,8 +20,6 @@
@pytest.mark.parametrize("model_ids", get_gguf_model_list())
@pytest.mark.precommit
def test_pipelines_with_gguf_generate(pipeline_type, model_ids):
if sys.platform == 'darwin':
pytest.skip(reason="168882: Sporadic segmentation fault failure on MacOS.")
Copy link
Collaborator

Choose a reason for hiding this comment

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

JIRA ticket is still opened: https://jira.devtools.intel.com/browse/CVS-168882
Where is the fix?

Copy link
Author

Choose a reason for hiding this comment

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

Right, our previous assumption that segment issue may related to limited disk storage in GHA CI machine, #2488 merged to mitigate this issue.

It turn out the segment fault issue it not related to disk storage issue, it is still not root cause and not reproducible in local mac machine from validation team.

Copy link
Collaborator

@rkazants rkazants Jul 31, 2025 •
edited
Loading

Choose a reason for hiding this comment

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

Looks the issue still exists

{7E33C766-6E0D-42C1-BB1B-6A04D55F28FD}

Copy link
Author

@sammysun0711 sammysun0711 Jul 31, 2025 •
edited
Loading

Choose a reason for hiding this comment

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

Yes, as I mentioned above, this segment fault issue still exists, and not found the root cause yet, may need your suggestions to move forward.

Copy link
Collaborator

Choose a reason for hiding this comment

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

You can ignore the problem assuming it's x86 specific. It's going to be dropped by OV: https://www.intel.com/content/www/us/en/developer/articles/release-notes/openvino/2025-2.html

MacOS x86 is no longer recommended for use due to the discontinuation of validation. Full support will be removed later in 2025.

I'd propose to switch to ticket 171090

gguf_model_id = model_ids["gguf_model_id"]
gguf_filename = model_ids["gguf_filename"]
dynamic_quantization_group_size = model_ids["dynamic_quantization_group_size"]
Expand Down Expand Up @@ -63,8 +61,6 @@ def test_pipelines_with_gguf_generate(pipeline_type, model_ids):
@pytest.mark.parametrize("enable_save_ov_model", [False, True])
@pytest.mark.precommit
def test_full_gguf_pipeline(pipeline_type, model_ids, enable_save_ov_model):
if sys.platform == 'darwin':
pytest.skip(reason="168882: Sporadic segmentation fault failure on MacOS.")
gguf_model_id = model_ids["gguf_model_id"]
gguf_filename = model_ids["gguf_filename"]
dynamic_quantization_group_size = model_ids["dynamic_quantization_group_size"]
Expand Down
Loading