Managing AI Inference Pipelines on Kubernetes with NVIDIA NIM Operator

Originally published at: https://developer.nvidia.com/blog/managing-ai-inference-pipelines-on-kubernetes-with-nvidia-nim-operator/

Developers have shown a lot of excitement for NVIDIA NIM microservices, a set of easy-to-use cloud-native microservices that shortens the time-to-market and simplifies the deployment of generative AI models anywhere, across cloud, data centers, cloud, and GPU-accelerated workstations.  To meet the demands of diverse use cases, NVIDIA is bringing to market a variety of different…

2 Likes

Congratulations Team on this release.
Is this NIMOperator now officially supported?

Yes, it is officially supported now.

Hello, I am trying to Install the NIM Operator on OpenShift cluster per the documentation. However, the operator bundle latest tag is missing and I have encountered the following error.

operator-sdk run bundle nvcr.io/nvidia/cloud-native/k8s-nim-operator:bundle-latest --namespace nvidia-nim-operator

FATA[0002] Failed to run bundle: pull bundle image: error pulling image nvcr.io/nvidia/cloud-native/k8s-nim-operator:bundle-latest: error resolving name for image ref nvcr.io/nvidia/cloud-native/k8s-nim-operator:bundle-latest: nvcr.io/nvidia/cloud-native/k8s-nim-operator:bundle-latest: not found