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

feat(ai.triton.server): expose "timeout" parameter for long running operations #4017

Merged
merged 24 commits into from
Jun 14, 2022

Conversation

mattdibi
Copy link
Contributor

@mattdibi mattdibi commented Jun 10, 2022

Exposed "timeout" parameter to the user for long running operations.

Description of the solution adopted: Added "timeout" (in seconds) for time consuming tasks like server startup, shutdown or model load. If the task exceeds the timeout the operation will be terminated with an error.

This "timeout" parameter substitutes the fixed number of attempts we were performing for the above-mentioned operations since the time taken by these heavily depends on hardware and software configuration (amount of model loaded in the server).

Additionally a new kill() method was added to the TritonServerLocalManager for killing a non-responsive process.

mattdibi added 22 commits June 10, 2022 09:46
Signed-off-by: Mattia Dal Ben <[email protected]>
Signed-off-by: Mattia Dal Ben <[email protected]>
@mattdibi mattdibi marked this pull request as ready for review June 13, 2022 07:12
@mattdibi
Copy link
Contributor Author

For whatever reason the Sonar status is missing. Here's the direct link.

Signed-off-by: Mattia Dal Ben <[email protected]>
@MMaiero MMaiero merged commit 90ce342 into eclipse-kura:develop Jun 14, 2022
@mattdibi mattdibi deleted the feat/expose_timeout branch June 14, 2022 07:58
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