first commit

tests/kustomize/vllm-server-loadbalancer/deployment-patch.yaml

@@ -0,0 +1,19 @@
+- op: replace
+  path: /spec/template/spec/containers/0/args/5
+  value: Qwen/Qwen2.5-7B-Instruct
+- op: replace
+  path: /spec/template/spec/containers/0/args/7
+  value: qwen2-5-7b
+- op: replace
+  path: /spec/template/spec/containers/0/resources/requests/cpu
+  value: "4"
+- op: replace
+  path: /spec/template/spec/containers/0/resources/requests/memory
+  value: 24Gi
+- op: replace
+  path: /spec/template/spec/containers/0/resources/limits/cpu
+  value: "8"
+- op: replace
+  path: /spec/template/spec/containers/0/resources/limits/memory
+  value: 48Gi
+

tests/kustomize/vllm-server-loadbalancer/generated-secret.yaml

@@ -0,0 +1,12 @@
+apiVersion: v1
+kind: Secret
+metadata:
+  name: vllm-secrets
+  labels:
+    app.kubernetes.io/name: vllm-server
+    app.kubernetes.io/component: auth
+    app.kubernetes.io/part-of: ocdp-workload
+type: Opaque
+stringData:
+  hfToken: ""
+

tests/kustomize/vllm-server-loadbalancer/kustomization.yaml

@@ -0,0 +1,22 @@
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+namespace: ocdp-workload-test
+nameSuffix: -test
+resources:
+  - ../../../apps/vllm-server/base
+  - generated-secret.yaml
+components:
+  - ../../../apps/vllm-server/components/gpu-nvidia
+  - ../../../apps/vllm-server/components/pvc-cache
+  - ../../../apps/vllm-server/components/service-loadbalancer
+patches:
+  - path: deployment-patch.yaml
+    target:
+      group: apps
+      version: v1
+      kind: Deployment
+      name: vllm-server
+  - path: pvc-patch.yaml
+    target:
+      kind: PersistentVolumeClaim
+      name: vllm-cache

tests/kustomize/vllm-server-loadbalancer/pvc-patch.yaml

@@ -0,0 +1,4 @@
+- op: replace
+  path: /spec/resources/requests/storage
+  value: 200Gi
+