Skip to Main Content
Deploy NVIDIA Inference Microservices (NIM) on Oracle Kubernetes Engine (OKE)

About This Workshop

Youtube Video

About This Workshop
In this workshop, you will learn how to deploy and manage NVIDIA NIM containers on Oracle Container Engine for Kubernetes (OKE) to run scalable, high-performance AI inference workloads. This session is designed for developers and MLOps engineers who want to operationalize NVIDIA AI models using Kubernetes-native workflows on OCI.

This workshop is ideal for developers, data scientists, and DevOps practitioners interested in:

- Deploying NIM on Kubernetes: Learn how to orchestrate and scale NVIDIA NIM containers using OKE for efficient AI inference in production.
- Harnessing NVIDIA GPUs for optimal performance: Experience how OKE integrates with NVIDIA GPU nodes to accelerate inference with TensorRT-optimized NIMs.
- Streamlining MLOps: Automate deployment, scaling, and lifecycle management of AI models using Helm, kubectl, and OCI DevOps tools within a unified cloud environment.

What you will learn
By the end of this workshop, you will have hands-on experience with:

- Creating an NVIDIA API Key and pulling NIM containers
- Setting up an OKE cluster with GPU-enabled nodes
- Deploying NVIDIA NIM using Helm or kubectl
- Exposing NIM services securely for inference
- Sending inference requests and monitoring performance with OCI tools

Workshop Info

  • Lab 1: Set up OKE Cluster
  • Lab 2: Install NVIDIA GPU Operator
  • Lab 3: Deploy the LLM NIM and testing the inference API
  • Familiarity with Oracle Cloud Infrastructure (OCI) is helpful
  • Familiarity with Oracle Kubernetes Engine (OKE) is helpful

Other Workshops you might like

Other Workshops you might like Cards