E2E Quickstart Example

# The operator image is supplied by the chart version (--version 0.4.5) — nothing to pin here.
engine:
  enabled: true
  spec:
    l1:
      sizeGB: 60
    image:
      repository: lmcache/vllm-openai
      tag: v0.4.5          # pin explicitly
      pullPolicy: IfNotPresent

# OpenShift only — grants the privileged SCC the engine's hostIPC needs.
# Delete this block on plain Kubernetes.
openshift:
  enabled: true

apiVersion: apps/v1
kind: Deployment
metadata:
  name: vllm-demo
  namespace: tensormesh-operator
  labels: { app: vllm-demo }
spec:
  replicas: 1
  selector: { matchLabels: { app: vllm-demo } }
  template:
    metadata: { labels: { app: vllm-demo } }
    spec:
      hostIPC: true                                            # required for MP mode
      serviceAccountName: tensormesh-operator-engine-privileged # reuse the chart's privileged SA
      nodeSelector:
        nvidia.com/gpu.present: "true"                         # colocate with the engine
      containers:
        - name: vllm
          image: lmcache/vllm-openai:v0.4.5   # pin explicitly, never :latest
          imagePullPolicy: IfNotPresent
          env:
            - { name: HF_HUB_DISABLE_TELEMETRY, value: "1" }
          command: ["/bin/sh", "-c"]
          args:
            - |
              exec python3 -m vllm.entrypoints.openai.api_server \
                --model Qwen/Qwen3-0.6B \
                --port 8000 \
                --gpu-memory-utilization 0.6 \
                --no-enable-prefix-caching \
                --max-model-len 32768 \
                --kv-transfer-config "$(cat /etc/lmcache/kv-transfer-config.json)"
          ports: [{ name: http, containerPort: 8000 }]
          volumeMounts:
            - { name: kv-transfer-config, mountPath: /etc/lmcache, readOnly: true }
            - { name: hf-cache,           mountPath: /root/.cache/huggingface }
          resources:
            limits:   { nvidia.com/gpu: "1", memory: 32Gi }
            # `memory` request is scheduler-accounting only; the limit is the real cap.
            # Lower this if the node is already heavily booked (e.g. the engine reserves
            # a large L1 cache in host memory).
            requests: { nvidia.com/gpu: "1", cpu: "2", memory: 6Gi }
          readinessProbe:
            httpGet: { path: /health, port: http }
            initialDelaySeconds: 60
            periodSeconds: 15
            failureThreshold: 40
      volumes:
        - name: kv-transfer-config
          configMap:
            name: tensormesh-operator-default-engine-connection
        - name: hf-cache
          emptyDir: { sizeLimit: 20Gi }
---
apiVersion: v1
kind: Service
metadata:
  name: inference
  namespace: tensormesh-operator
spec:
  selector: { app: vllm-demo }
  ports: [{ name: http, port: 8000, targetPort: http }]

apiVersion: batch/v1
kind: Job
metadata:
  name: lmcache-benchmark
  namespace: tensormesh-operator
spec:
  backoffLimit: 0
  ttlSecondsAfterFinished: 3600
  template:
    metadata:
      labels: { app: lmcache-benchmark }
    spec:
      restartPolicy: Never
      nodeSelector:
        nvidia.com/gpu.present: "true"   # reuse the cached vLLM image; the client needs no GPU
      containers:
        - name: bench
          image: lmcache/vllm-openai:v0.4.5
          imagePullPolicy: IfNotPresent
          env:
            - { name: HF_HOME, value: /tmp/hf }   # writable under OpenShift's random UID
            - { name: HF_HUB_DISABLE_TELEMETRY, value: "1" }
          command: ["/bin/sh", "-c"]
          args:
            - |
              set -e
              run() {
                vllm bench serve --backend openai --base-url http://inference:8000 \
                  --model Qwen/Qwen3-0.6B --dataset-name random \
                  --num-prompts 20 --random-input-len 20480 \
                  --random-output-len 1 --seed 32
              }
              echo "### PASS 1 (cold) ###"; run
              sleep 5
              echo "### PASS 2 (warm) ###"; run
          volumeMounts:
            - { name: hf, mountPath: /tmp/hf }
          resources:
            requests: { cpu: "1", memory: 2Gi }
            limits:   { cpu: "2", memory: 4Gi }
      volumes:
        - { name: hf, emptyDir: {} }