OpenVINO™ Model Server Operator

Description

OpenVINO™ Model Server (OVMS) is a scalable, high-performance solution for serving machine learning models optimized for Intel® architectures. The server provides an inference service via gRPC or REST API - making it easy to deploy new algorithms and AI experiments using the same architecture as TensorFlow Serving for any models trained in a framework that is supported by OpenVINO.

About this Operator

This Operator is based on a Helm chart for OpenVINO Model Server. It supports all available parameters from the helm chart.

Using the cluster

OpenVINO Model Server can be consumed as a Service with the name matching the Ovms record.

kubectl get pods
NAME READY STATUS RESTARTS AGE
ovms-sample-586f6f76df-dpps4 1/1 Running 0 8h

kubectl get services
NAME TYPE CLUSTER-IP EXTERNAL-IP PORT(S) AGE
ovms-sample ClusterIP 172.25.199.210 <none> 8080/TCP,8081/TCP 8h

Before you start

Depending on the deployment configuration there might be pre-requisites for additional records to be created in the cluster.

References

OpenVINO Model Server on Github

Licenses

LEGAL NOTICE: By accessing, downloading or using this software and any required dependent software (the “Software Package”), you agree to the terms and conditions of the software license agreements for the Software Package, which may also include notices, disclaimers, or license terms for third party software included with the Software Package. Please refer to the “third-party-programs.txt” or other similarly-named text file for additional details.

The OpenVINO™ Model Server Operator is released under Apache2 license. As for any pre-built image usage, it is the image user's responsibility to ensure that any use of this image complies with any relevant licenses and potential fees for all software contained within. We will have no indemnity or warranty coverage from suppliers.

Components:

• Red Hat* UBI
• Helm operator
• OVMS operator
• OVMS