llama.cpp fixed DNS

Reviewed-on: #406

k8s/apps/llamacpp/app.yaml

@@ -0,0 +1,20 @@
+apiVersion: argoproj.io/v1alpha1
+kind: Application
+metadata:
+  name: llamacpp
+  namespace: argocd
+spec:
+  project: apps
+  destination:
+    namespace: llamacpp
+    server: https://kubernetes.default.svc
+  source:
+    repoURL: ssh://git@gt.hexor.cy:30022/ab/homelab.git
+    targetRevision: HEAD
+    path: k8s/apps/llamacpp
+  syncPolicy:
+    automated:
+      selfHeal: true
+      prune: true
+    syncOptions:
+      - CreateNamespace=true

k8s/apps/llamacpp/configmap.yaml

@@ -0,0 +1,12 @@
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: llamacpp-config
+data:
+  LLAMA_CACHE: /models
+  LLAMA_ARG_HOST: 0.0.0.0
+  LLAMA_ARG_PORT: "8080"
+  LLAMA_ARG_HF_REPO: "unsloth/Qwen3.6-35B-A3B-MTP-GGUF:UD-Q6_K"
+  LLAMA_ARG_CTX_SIZE: "32768"
+  LLAMA_ARG_FLASH_ATTN: auto
+  LLAMA_ARG_FIT: "on"

k8s/apps/llamacpp/deployment.yaml

@@ -0,0 +1,71 @@
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: llamacpp
+  annotations:
+    reloader.stakater.com/auto: "true"
+  labels:
+    app: llamacpp
+spec:
+  replicas: 1
+  strategy:
+    type: Recreate
+  selector:
+    matchLabels:
+      app: llamacpp
+  template:
+    metadata:
+      labels:
+        app: llamacpp
+    spec:
+      dnsPolicy: Default
+      nodeSelector:
+        kubernetes.io/hostname: ai.tail2fe2d.ts.net
+      tolerations:
+        - key: workload
+          operator: Equal
+          value: ai
+          effect: NoSchedule
+      containers:
+        - name: llamacpp
+          image: ghcr.io/ggml-org/llama.cpp:server-rocm-b9501 
+          imagePullPolicy: IfNotPresent
+          envFrom:
+            - configMapRef:
+                name: llamacpp-config
+          env:
+            - name: HF_TOKEN
+              valueFrom:
+                secretKeyRef:
+                  name: llamacpp-hf-token
+                  key: token
+                  optional: true
+          ports:
+            - name: http
+              containerPort: 8080
+              protocol: TCP
+          resources:
+            limits:
+              amd.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: /k8s/llamacpp/models
+            type: DirectoryOrCreate

k8s/apps/llamacpp/kustomization.yaml

@@ -0,0 +1,8 @@
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+
+resources:
+  - app.yaml
+  - configmap.yaml
+  - deployment.yaml
+  - service.yaml

k8s/apps/llamacpp/service.yaml

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

k8s/core/gpu/amd-gpu-values.yaml

@@ -0,0 +1,31 @@
+nfd:
+  enabled: false
+
+labeller:
+  enabled: false
+
+dp:
+  image:
+    repository: docker.io/rocm/k8s-device-plugin
+    tag: "1.31.0.9"
+  updateStrategy:
+    type: RollingUpdate
+    rollingUpdate:
+      maxUnavailable: 1
+
+securityContext:
+  allowPrivilegeEscalation: false
+  capabilities:
+    drop:
+      - ALL
+
+tolerations:
+  - key: workload
+    operator: Equal
+    value: ai
+    effect: NoSchedule
+
+node_selector_enabled: true
+node_selector:
+  kubernetes.io/arch: amd64
+  kubernetes.io/hostname: ai.tail2fe2d.ts.net

k8s/core/gpu/kustomization.yaml

@@ -13,3 +13,24 @@ helmCharts:
     namespace: gpu-system
     valuesFile: values.yaml
     includeCRDs: true
+  - name: amd-gpu
+    repo: https://rocm.github.io/k8s-device-plugin/
+    version: 0.21.0
+    releaseName: amd-gpu-device-plugin
+    namespace: gpu-system
+    valuesFile: amd-gpu-values.yaml
+    includeCRDs: true
+
+patches:
+  - target:
+      group: apps
+      version: v1
+      kind: DaemonSet
+      name: amd-gpu-device-plugin-daemonset
+      namespace: gpu-system
+    patch: |-
+      - op: replace
+        path: /spec/template/spec/nodeSelector
+        value:
+          kubernetes.io/arch: amd64
+          kubernetes.io/hostname: ai.tail2fe2d.ts.net