This quickstart will serve a small language model on CPUs, using vLLM inference runtime

Deploys Llama 3.2-3B on vLLM with Llama Stack and MCP servers in OpenShift AI.

Llama Stack Observability quickstart

AI quickstart for deploying an LLM with Tool Calling enabled on top of OpenShift AI

Dynamically route user prompts to LoRA adapters or a base LLM using semantic evaluation on Red Hat OpenShift AI with LiteLLM and vLLM.

RHOAI Metrics Dashboard for Single Serving Models

An easy way to quickly add a lot of useful, community-provided, custom Workbench Images

This is a sample Partner AI Quickstart for demo purpose.