Skip to content

Conversation

@yangligt2
Copy link

Fixes #140

@yangligt2
Copy link
Author

Also added temporary and basic test suite to validate the chart's rendering logic. It is intended as a stopgap solution until a more formal testing framework.

@@ -0,0 +1,14 @@
# Test values for default accelerator resource behavior.
# The chart should automatically set the GPU count to match tensor parallelism.
Copy link
Collaborator

Choose a reason for hiding this comment

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

Should the default match tensor x data?

modelCommand: vllmServe
resources:
limits:
nvidia.com/gpu: "8" # User-defined value
Copy link
Collaborator

Choose a reason for hiding this comment

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

Would this still work if I want to set gpu to 0? For example, for vLLM simulators that won't require GPUs but the args would still use tensor-parallel-size=2.

Comment on lines +15 to +16
echo "Running Helm template rendering tests..."
echo "========================================"
Copy link
Collaborator

Choose a reason for hiding this comment

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

This is really nice. I wonder if you want to include this as part of the Lint/Test Chart github action workflow.

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.

acceleratorResource is enforced to be equal to tensorParallelism

2 participants