Skip to content

Enable Nsys gpu device metrics #257

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

Merged
merged 2 commits into from
Jun 10, 2025

Conversation

ashbhandare
Copy link
Contributor

GPU metrics must only be enabled on a single rank on a node for a distributed job while profiling with nsys.

@ashbhandare ashbhandare marked this pull request as ready for review June 9, 2025 16:59
@hemildesai
Copy link
Contributor

Looks good mostly, can you add a test for this in test/core/execution/test_launcher.py?

@hemildesai
Copy link
Contributor

Also, you will need to signoff your commits to pass the DCO check.

Aishwarya Bhandare and others added 2 commits June 9, 2025 17:07
Signed-off-by: ashbhandare <[email protected]>
Signed-off-by: ashbhandare <[email protected]>
role.entrypoint = "nsys"
role.args = nsys_prefix + role.args
role.entrypoint, nsys_postfix = executor.get_nsys_entrypoint()
role.args = nsys_prefix + role.args + [nsys_postfix]
Copy link
Contributor

Choose a reason for hiding this comment

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

Can you wrap this in an if condition? i.e. only add the postfix if its not empty.

@hemildesai hemildesai merged commit f3e69ee into NVIDIA-NeMo:main Jun 10, 2025
16 checks passed
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.

2 participants