sriram-dsl

logs : ``` [2024-10-08 09:51:34.769][1][modelmanager][debug][modelinstance.cpp:737] Model: model1; version: 1; target device: CPU, CompiledModel config key: OPTIMAL_NUMBER_OF_ _ _ [2024-10-08 09:51:34.769][1][modelmanager][debug][modelinstance.cpp:737] Model: model1; version: 1; target device: CPU, CompiledModel config key:...

I have been using this OpenVINO server for the last two years without any issues. However, we started encountering this problem in the most recent deployments, even though we are...

Sorry for the delayed response. We have tried it, but it didn't work. Now, this issue is occurring in every deployment. We are running inference containers outside the cluster. Could...

Outside of Kubernetes, it is working fine. The previous deployments done on Kubernetes are facing the issue. I will try removing all limitations inside the cluster.

this issue still persists this is the docker stats of the openvino container outside the cluster  this is the docker stats of the openvino container inside the cluster ...

How can I measure throughput effectively? Is there a tool similar to NVIDIA’s perf_analyzer that I can use for this purpose? Additionally, if I deploy a container within a Kubernetes...

 * `cpu_reservation` tag is not working ##It is taking 2cores when i load a single model, which is expected  ##For a single model, iam getting a throughput of...

i have tried with `2025.1` it is not giving issue for cpu reservation tag but i have not done the benchmarking, i wil do it and update