Radion Bikmukhamedov

I wish this was implemented, moreover, I thought this is what the model schema was needed for!

I have noticed that timestamps of incremental materialization are stored in the registry and are sent to client as well. We run incr. mat. every 15 min, so over month...

I have never adjusted registry cache TTL, it has always been set to the default value.

an update from us: having disabled incremental materialization for a week, we do NOT notice increases in latency anymore, which confirms my hypothesis above. As you at the chart below,...

we found that logging to feast caused the problem, we disabled it and everything runs without leaks now

I might have left the last comment in a wrong issue. So the current status is: - we disabled feast's telemetry to help with a memory leak problem we had...

hey! please, check the readme here: https://github.com/RadionBik/ML-based-network-traffic-classifier/tree/master/gpt_model#pre-trained-models-and-datasets the data must be available if you follow the steps described there.