Skip to content
This repository has been archived by the owner on Dec 11, 2024. It is now read-only.

Test MLPerf inference loadgen to automatically determine the thoughput of a system #17

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

Comments

@arjunsuresh
Copy link

arjunsuresh commented Oct 18, 2024

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 subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant