Auto-update README with current k8s applications

Generated by CI/CD workflow on 2026-06-17 00:24:38

This PR updates the README.md file with the current list of applications found in the k8s/ directory structure.

k8s/apps/llamacpp/configmap-cuda.yaml

@@ -1,12 +0,0 @@
-apiVersion: v1
-kind: ConfigMap
-metadata:
-  name: llamacpp-cuda-config
-data:
-  LLAMA_CACHE: /models
-  LLAMA_ARG_HOST: 0.0.0.0
-  LLAMA_ARG_PORT: "8080"
-  LLAMA_ARG_HF_REPO: "unsloth/gemma-4-12b-it-GGUF:Q6_K"
-  LLAMA_ARG_CTX_SIZE: "32768"
-  LLAMA_ARG_FLASH_ATTN: auto
-  LLAMA_ARG_FIT: "on"

k8s/apps/llamacpp/deployment-cuda.yaml

@@ -1,72 +0,0 @@
-apiVersion: apps/v1
-kind: Deployment
-metadata:
-  name: llamacpp-cuda
-  annotations:
-    reloader.stakater.com/auto: "true"
-  labels:
-    app: llamacpp-cuda
-spec:
-  replicas: 1
-  strategy:
-    type: Recreate
-  selector:
-    matchLabels:
-      app: llamacpp-cuda
-  template:
-    metadata:
-      labels:
-        app: llamacpp-cuda
-    spec:
-      dnsPolicy: Default
-      runtimeClassName: nvidia
-      nodeSelector:
-        kubernetes.io/hostname: uk-desktop.tail2fe2d.ts.net
-      tolerations:
-        - key: workload
-          operator: Equal
-          value: desktop
-          effect: NoSchedule
-      containers:
-        - name: llamacpp
-          image: ghcr.io/ggml-org/llama.cpp:server-cuda-b9501
-          imagePullPolicy: IfNotPresent
-          envFrom:
-            - configMapRef:
-                name: llamacpp-cuda-config
-          env:
-            - name: HF_TOKEN
-              valueFrom:
-                secretKeyRef:
-                  name: llamacpp-hf-token
-                  key: token
-                  optional: true
-          ports:
-            - name: http
-              containerPort: 8080
-              protocol: TCP
-          resources:
-            limits:
-              nvidia.com/gpu: 1
-          startupProbe:
-            httpGet:
-              path: /health
-              port: http
-            failureThreshold: 180
-            periodSeconds: 10
-            timeoutSeconds: 5
-          readinessProbe:
-            httpGet:
-              path: /health
-              port: http
-            failureThreshold: 3
-            periodSeconds: 10
-            timeoutSeconds: 5
-          volumeMounts:
-            - name: models
-              mountPath: /models
-      volumes:
-        - name: models
-          hostPath:
-            path: /data/llama.cpp/models
-            type: DirectoryOrCreate

k8s/apps/llamacpp/kustomization.yaml

@@ -3,9 +3,6 @@ kind: Kustomization
 
 resources:
   - app.yaml
-  - configmap-cuda.yaml
   - configmap.yaml
-  - deployment-cuda.yaml
   - deployment.yaml
-  - service-cuda.yaml
   - service.yaml

k8s/apps/llamacpp/service-cuda.yaml

@@ -1,15 +0,0 @@
-apiVersion: v1
-kind: Service
-metadata:
-  name: llamacpp-cuda
-  labels:
-    app: llamacpp-cuda
-spec:
-  type: ClusterIP
-  selector:
-    app: llamacpp-cuda
-  ports:
-    - name: http
-      port: 8080
-      targetPort: http
-      protocol: TCP

k8s/apps/pasarguard/deployment.yaml

@@ -11,7 +11,7 @@ spec:
   selector:
     matchLabels:
       app: pasarguard
-  replicas: 2
+  replicas: 1
   strategy:
     type: RollingUpdate
   template: