Lucian Carata

@charleschangdp In order to help you with the issue, it would be helpful to understand more about the setup of the test and the way Seldon Core 2 is configured:...

Thank you for the update, we'll look into this. Some of the degradation in throughput will be caused by one `dataflow-engine` replica going away, but not all of it --...

That's helpful, thank you for the additional test and details. The response time statistics show that less than 10% of requests time out, but at least 5% (because the 90th...

For reference, this is related to [#2285]. Will be fixed in MLServer 1.7.2, and we also recommend pinning `uvloop` to `0.21.0` until the patch release is out.

Hi @GrantDeljevic! Thank you for the proposed fix, we are also aware of the issue. We're aiming to issue a patch release (1.7.2) containing the fix within the next week...