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

Test MLPerf inference loadgen to automatically determine the thoughput of a system #398

Open
arjunsuresh opened this issue Oct 18, 2024 · 0 comments

Comments

@arjunsuresh
Copy link
Contributor

We need to add in CM a way to automatically determine the throughput of a system using loadgen. This PR adds a <enforce_max_duration< option to loadgen - but not exactly sure, if it'll serve our purpose.

Currently, we have to provide an expected target_qps for a system and if we don't loadgen assumes this to be 1. What we ideally want is to keep loadgen running for say 5 minutes and then take the number of samples processed. So, the loadgen should keep sending the queries until 5 minutes are over.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Development

No branches or pull requests

1 participant