Skip to content
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

Return an error if --load-model is specified without explicit model control mode #7259

Merged
merged 2 commits into from
May 22, 2024

Conversation

rmccorm4
Copy link
Contributor

@rmccorm4 rmccorm4 commented May 22, 2024

Before: Specifying --load-model without explicit model control mode will silently not work as expected, and instead load all models with the default model control mode.

root@ced35d0-lcedt:/opt/tritonserver# tritonserver --model-repository models --load-model my_model
...
I0522 18:28:47.526658 448 http_server.cc:4692] Started HTTPService at 0.0.0.0:8000

After: Specifying --load-model without explicit model control mode will fail, and prompt you to also set --model-control-mode=explicit. Parsing errors will also be reported at the bottom for immediate visibility.

root@ced35d0-lcedt:/opt/tritonserver# tritonserver --model-repository models --load-model abc
...
LONG
HELP
OUTPUT
...
# NEW: Log error for invalid arg, and log ParseException errors at the bottom as well for easier visibility
Error: Use of '--load-model' requires setting '--model-control-mode=explicit' as well.

NOTE: This error can be undone if/when we add support for --load-model in default model control mode.

Copy link
Contributor

@debermudez debermudez left a comment

Choose a reason for hiding this comment

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

woohoo

@rmccorm4 rmccorm4 merged commit ab160fb into main May 22, 2024
3 checks passed
@rmccorm4 rmccorm4 deleted the rmccormick-load-model-warning branch May 22, 2024 22:47
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Development

Successfully merging this pull request may close these issues.

4 participants