Skip to main content

Kubernetes LLM Labs

The labs turn the guide into operator challenges. The docs remain free, indexable runbooks. The interactive version lives at labs.k8sllm.online, where you can type commands in a lab terminal, inspect Kubernetes output, unlock hints, reveal solutions, and keep private progress on your device.

Challenge of the Week

Start with the vLLM Inference Challenge. It is the best first demo because it checks the core platform loop: GPU placement, model runtime readiness, token latency, queue wait, and production evidence.

Entry pointLink
Interactive challengeStart vLLM Inference Challenge
Production deployment guidevLLM Kubernetes Production Deployment
Readiness lead magnetLLM Production Readiness Checklist
Product roadmapKubernetes LLM Platform Roadmap
Interactive MVP12free browser-guided challenges

K8sLLM Labs is moving from static runbooks into an interactive lab product at labs.k8sllm.online. V1 uses browser-side checks, local progress, hints, and solution reveal tracking. Hosted sandboxes and paid lab packs come later after auth, abuse controls, and infrastructure cost limits are designed.

Topic
Difficulty
Path
Lab signal

Showing 12 of 12 challenges.

Model servingHard75 minFree

vLLM Inference Challenge

Deploy a GPU-backed OpenAI-compatible endpoint and prove scheduling, health, TTFT, queueing, and rollback readiness.

Persona
AI infrastructure engineer
Tools
kubectl, vLLM, Prometheus
Checks
6
RAGMedium60 minFree

RAG Retrieval Challenge

Operate ingestion, metadata filters, vector retrieval, answer evaluation, and failure drills for production RAG.

Persona
MLOps engineer
Tools
kubectl, curl, vector database
Checks
6
ProductionHard50 minFree

Production Readiness Challenge

Run a launch review across security, quota, rollout, observability, cost, and ownership before live traffic.

Persona
Platform lead
Tools
kubectl, policy engine, dashboard
Checks
6
ObservabilityMedium45 minFree

LLM Observability Challenge

Build the signal model needed to debug user latency, runtime saturation, GPU pressure, traces, logs, and alerts.

Persona
SRE
Tools
Prometheus, Grafana, OpenTelemetry
Checks
6
Model servingMedium55 minFree

vLLM Kubernetes Deployment Lab

Design the deployment contract for vLLM with model cache, readiness, runtime flags, and service exposure.

Persona
AI infrastructure engineer
Tools
kubectl, vLLM, container registry
Checks
6
ArchitectureMedium35 minFree

KServe vs Ray Serve Decision Lab

Choose the serving abstraction by ownership model, CRDs, graph complexity, autoscaling, and rollout needs.

Persona
Platform architect
Tools
decision matrix, runtime inventory
Checks
4
GPU capacityHard65 minFree

GPU Node Pool Scheduling Lab

Prove accelerator placement with labels, taints, tolerations, quotas, and unschedulable-pod debugging.

Persona
Platform engineer
Tools
kubectl, NVIDIA device plugin, cluster autoscaler
Checks
6
RAGHard70 minFree

RAG Retrieval Quality Lab

Measure retrieval recall, citation accuracy, tenant filtering, and reranking latency before generation.

Persona
MLOps engineer
Tools
evaluation set, vector database, reranker
Checks
6
CostMedium45 minFree

Inference Cost Model Lab

Calculate cost per request from input tokens, output tokens, GPU profile, utilization, and cache behavior.

Persona
AI platform lead
Tools
spreadsheet, metrics export, benchmark report
Checks
4
ProductionHard60 minFree

LLM Rollout and Rollback Lab

Design traffic shifting, readiness gates, rollback triggers, and model-version ownership for inference services.

Persona
SRE
Tools
Argo CD, gateway policy, metrics dashboard
Checks
6
SecurityHard70 minFree

Multi-Tenant LLM Security Lab

Review tenant routing, namespace boundaries, secrets, NetworkPolicy, prompt logging, and retrieval authorization.

Persona
Security-minded platform engineer
Tools
kubectl, NetworkPolicy, admission policy
Checks
6
ObservabilityMedium50 minFree

LLM Observability and Cost Dashboard Lab

Create a dashboard model that joins user latency, queue wait, GPU pressure, token throughput, and cost signals.

Persona
SRE
Tools
Prometheus, Grafana, OpenTelemetry
Checks
6

Lab prerequisites

RequirementWhy it matters
Kubernetes cluster accessYou need namespace, workload, service, and log visibility.
GPU node pool for inference labsLLM serving exercises depend on accelerator scheduling and runtime health.
Metrics stackPrometheus, Grafana, OpenTelemetry, or equivalent telemetry makes validation concrete.
GitOps or manifest workflowLabs are easier to review when every change is versioned.
Test prompts and evaluation casesLLM workloads need behavior checks, not only pod readiness.

How to use the labs

  1. Read the related architecture guide before applying manifests.
  2. Open the matching interactive challenge at labs.k8sllm.online/challenges.
  3. Run the challenge scenario in your own cluster or mock environment.
  4. Paste command output into the guided checks and use hints only when blocked.
  5. Trigger one failure drill and record which signal detected the failure first.

New labs should follow the Content Review Checklist: objective, prerequisites, manifests or commands, validation signals, failure drills, and expected signals.

Lab experience

CapabilityWhy it matters
Lab terminalPractice Kubernetes and LLM platform commands in the flow of the challenge.
Guided checksValidate evidence such as GPU placement, model readiness, metrics, and policy boundaries.
Progressive hintsKeep moving without turning every lab into a copy-paste answer sheet.
Private device progressResume challenges on the same device without creating an account.
Downloadable kitsFuture lab packs can include manifests, failure drills, worksheets, and deeper solution reviews.

Start with K8s LLM: Kubernetes LLM Platform Guide, continue to GPU Node Pool Kubernetes, run the vLLM Inference Challenge, then move to RAG on Kubernetes and the RAG Retrieval Challenge.