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

Refactor Python backend tests #2945

Merged
merged 1 commit into from
Jun 2, 2021
Merged

Refactor Python backend tests #2945

merged 1 commit into from
Jun 2, 2021

Conversation

Tabrizian
Copy link
Member

This PR breaks the Python backend tests into multiple subsections. It also fixes a minor bug in server where the Triton server was not calling the backend destructors after it has become ready.

if (!StartEndpoints(server, trace_manager, shm_manager)) {
exit(1);
}

Copy link
Member Author

Choose a reason for hiding this comment

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

I moved the registration of endpoints after the registration of signal handling so that when the server is ready the destructors are called properly.

@Tabrizian Tabrizian merged commit 2c9bc8d into main Jun 2, 2021
@Tabrizian Tabrizian deleted the imant-py-leak branch June 2, 2021 13:57
maaquib pushed a commit to maaquib/server that referenced this pull request Jun 3, 2021
maaquib pushed a commit to maaquib/server that referenced this pull request Jun 3, 2021
deadeyegoodwin pushed a commit that referenced this pull request Jun 11, 2021
* Refactor Python backend tests (#2945)

* Update GKE deployer to 21.05, add scripts for benchmarking (#2942)

* upgrade to 21.05, add sample benchmark materials

* configuration change

* fix major

* fix major

* Update README.md

* add client deployment

* Fix wrong value in credentials for AWS Helm Chart (#2950)

* Fix wrong value in credentials for AWS Helm Chart

* Secrets.yaml deleted from gcp as it's not used

* Use device specific input in the input collector and backend (#2898)

* Use device specific input in the input collector and backend

* Draft: Add host policy changes

* Remove testing redirection

* Update according to review comments

* Use fallback input buffer properties consistently

* Update comment

Co-authored-by: msridhara <msridhara@msridhara-ub-desktop.nvidia.com>

* Add non-default model name support to Sagemaker serve script

Co-authored-by: Iman Tabrizian <itabrizian@nvidia.com>
Co-authored-by: Dong <mengdong@users.noreply.github.com>
Co-authored-by: Martin Beyer <tinchobeyer2@gmail.com>
Co-authored-by: madhu-nvda <77174106+madhu-nvda@users.noreply.github.com>
Co-authored-by: msridhara <msridhara@msridhara-ub-desktop.nvidia.com>
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.

2 participants