[Bugfix] Apply function module marker per-model instead of hardcoding diffusion (#5875)

Signed-off-by: khairulkabir1661 <khairulkabir1661@users.noreply.github.com>
Co-authored-by: khairulkabir1661 <khairulkabir1661@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>

tests/model_tests/diffusion/test_common_offline.py

@@ -21,8 +21,8 @@ from tests.model_tests.diffusion.task_runners import (
     run_and_validate_text_to_video_request,
 )
 
-# NOTE : Hardware marks are added dynamically based on test requirements
-pytestmark = [pytest.mark.diffusion, pytest.mark.xdist]
+# NOTE: Hardware and model type marks are added dynamically based on test requirements and model type
+pytestmark = [pytest.mark.xdist]
 
 
 @pytest.mark.parametrize(