Interactive challenge
vLLM Inference Challenge
Deploy a GPU-backed OpenAI-compatible endpoint and prove scheduling, health, TTFT, queueing, and rollback readiness.
Difficulty
Hard
Duration
75 min
Persona
AI infrastructure engineer
Tools
kubectl, vLLM, Prometheus
Prerequisites
GPU node poolGPU scheduling basicsModel artifact access
Active step 01
Prepare the platform boundary
Create or identify the namespace, labels, and ownership metadata that make the workload reviewable.
lab@k8sllm:llm-serving
Kubernetes context is loaded. Type commands directly or run the step sequence.