Skip to content

Add fix for devices that do not have memory resources #6823

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

Merged
rapids-bot merged 13 commits into from
Aug 27, 2025
Merged

Add fix for devices that do not have memory resources #6823

Changes from 1 commit
Commits
Show all changes
13 commits
Select commit Hold shift + click to select a range
a54c313
Add fix for devices that do not have memory resources
viclafargue May 30, 2025
2dc6c17
Merge branch 'branch-25.10' into fix-conftest-no-mem-res
viclafargue Aug 4, 2025
b4f2c85
Assuming at least 4GB memory
viclafargue Aug 4, 2025
1f8b2c1
Switching to pynvml
viclafargue Aug 4, 2025
7f9c957
bytes to GB
viclafargue Aug 4, 2025
3c49669
Adding pynvml as a dependency
viclafargue Aug 4, 2025
a0230fd
Fixing typo
viclafargue Aug 4, 2025
965f0d4
answering review
viclafargue Aug 5, 2025
114f3dd
Merge branch 'branch-25.10' into fix-conftest-no-mem-res
viclafargue Aug 11, 2025
507fbfe
Merge branch 'branch-25.10' into fix-conftest-no-mem-res
viclafargue Aug 14, 2025
c66fb47
Merge branch 'branch-25.10' into fix-conftest-no-mem-res
viclafargue Aug 25, 2025
711c6e9
Merge branch 'branch-25.10' into fix-conftest-no-mem-res
viclafargue Aug 26, 2025
e70314b
Merge branch 'branch-25.10' into fix-conftest-no-mem-res
viclafargue Aug 26, 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
7 changes: 5 additions & 2 deletions python/cuml/cuml/tests/conftest.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -287,8 +287,11 @@ def _get_gpu_memory():
if len(tokens) > 1:
gpus_memory.append(int(tokens[0]))
gpus_memory.sort()
max_gpu_memory = ceil(gpus_memory[-1] / 1024)
return max_gpu_memory
if len(gpus_memory) > 0:
max_gpu_memory = ceil(gpus_memory[-1] / 1024)
return max_gpu_memory
else:
return None
Copy link
Contributor

@csadorf csadorf May 30, 2025

Choose a reason for hiding this comment

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

I don't think returning None here is a good idea, because it would lead to TypeErrors in many of our (stress) tests.

Copy link
Contributor Author

@viclafargue viclafargue Jun 2, 2025

Choose a reason for hiding this comment

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

What do you recommend? Would returning 0 be a good solution?

Copy link
Contributor

@csadorf csadorf Jun 2, 2025

Choose a reason for hiding this comment

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

The only place we use this function is to set pytest.max_gpu_memory. That variable is implicitly expected to be a nonzero integer number wherever it is used.

I think using None is ok to indicate "unknown", but then we need to make sure to test for that wherever pytest.max_gpu_memory is used.



# =============================================================================
Expand Down