charleschangdp
charleschangdp
1. `ModelsReady` remains `True` 2. 4 partitions 3. 4 4. 4 replicas for each 5. 1 6. Inference servers are set to 2 replicas that are scheduled to run on...
I agree that a test that targets a specific RPS would provide some more insights. For the Locust test, since we know the Pipeline is impaired for about a minute,...
@lc525 Following up to see if you have made any progress on this topic.
We've implemented a Karpenter node group with ondemand instances dedicated to data-flow-engine pods. Every X number of days, Karpenter still need to roll these nodes per our infosec policy. Thus...