llama.cpp fixed DNS

llama.cpp fixed model name
pinned llama.cpp to server-rocm-b9501
2026-06-04 18:47:10 +03:00 · 2026-06-04 18:37:20 +03:00 · 2026-06-04 17:24:50 +03:00 · 2026-06-04 17:19:19 +03:00 · 2026-06-04 16:59:58 +03:00 · 2026-06-04 16:46:49 +03:00
10 changed files with 190 additions and 6 deletions
@@ -13,15 +13,19 @@ ArgoCD homelab project
 | Application | Status |
 | :--- | :---: |
 | **argocd** | [![argocd](https://ag.hexor.cy/api/badge?name=argocd&revision=true)](https://ag.hexor.cy/applications/argocd/argocd) |
+| **auth-proxy** | [![auth-proxy](https://ag.hexor.cy/api/badge?name=auth-proxy&revision=true)](https://ag.hexor.cy/applications/argocd/auth-proxy) |
 | **authentik** | [![authentik](https://ag.hexor.cy/api/badge?name=authentik&revision=true)](https://ag.hexor.cy/applications/argocd/authentik) |
 | **cert-manager** | [![cert-manager](https://ag.hexor.cy/api/badge?name=cert-manager&revision=true)](https://ag.hexor.cy/applications/argocd/cert-manager) |
 | **external-secrets** | [![external-secrets](https://ag.hexor.cy/api/badge?name=external-secrets&revision=true)](https://ag.hexor.cy/applications/argocd/external-secrets) |
 | **gpu** | [![gpu](https://ag.hexor.cy/api/badge?name=gpu&revision=true)](https://ag.hexor.cy/applications/argocd/gpu) |
+| **kanidm** | [![kanidm](https://ag.hexor.cy/api/badge?name=kanidm&revision=true)](https://ag.hexor.cy/applications/argocd/kanidm) |
+| **keycloak** | [![keycloak](https://ag.hexor.cy/api/badge?name=keycloak&revision=true)](https://ag.hexor.cy/applications/argocd/keycloak) |
 | **kube-system-custom** | [![kube-system-custom](https://ag.hexor.cy/api/badge?name=kube-system-custom&revision=true)](https://ag.hexor.cy/applications/argocd/kube-system-custom) |
 | **kubernetes-dashboard** | [![kubernetes-dashboard](https://ag.hexor.cy/api/badge?name=kubernetes-dashboard&revision=true)](https://ag.hexor.cy/applications/argocd/kubernetes-dashboard) |
 | **longhorn** | [![longhorn](https://ag.hexor.cy/api/badge?name=longhorn&revision=true)](https://ag.hexor.cy/applications/argocd/longhorn) |
 | **postgresql** | [![postgresql](https://ag.hexor.cy/api/badge?name=postgresql&revision=true)](https://ag.hexor.cy/applications/argocd/postgresql) |
 | **prom-stack** | [![prom-stack](https://ag.hexor.cy/api/badge?name=prom-stack&revision=true)](https://ag.hexor.cy/applications/argocd/prom-stack) |
+| **reloader** | [![reloader](https://ag.hexor.cy/api/badge?name=reloader&revision=true)](https://ag.hexor.cy/applications/argocd/reloader) |
 | **system-upgrade** | [![system-upgrade](https://ag.hexor.cy/api/badge?name=system-upgrade&revision=true)](https://ag.hexor.cy/applications/argocd/system-upgrade) |

 ### Games
@@ -39,8 +43,7 @@ ArgoCD homelab project
 | Application | Status |
 | :--- | :---: |
 | **comfyui** | [![comfyui](https://ag.hexor.cy/api/badge?name=comfyui&revision=true)](https://ag.hexor.cy/applications/argocd/comfyui) |
-| **furumi-dev** | [![furumi-dev](https://ag.hexor.cy/api/badge?name=furumi-dev&revision=true)](https://ag.hexor.cy/applications/argocd/furumi-dev) |
-| **furumi-server** | [![furumi-server](https://ag.hexor.cy/api/badge?name=furumi-server&revision=true)](https://ag.hexor.cy/applications/argocd/furumi-server) |
+| **furumi** | [![furumi](https://ag.hexor.cy/api/badge?name=furumi&revision=true)](https://ag.hexor.cy/applications/argocd/furumi) |
 | **gitea** | [![gitea](https://ag.hexor.cy/api/badge?name=gitea&revision=true)](https://ag.hexor.cy/applications/argocd/gitea) |
 | **greece-notifier** | [![greece-notifier](https://ag.hexor.cy/api/badge?name=greece-notifier&revision=true)](https://ag.hexor.cy/applications/argocd/greece-notifier) |
 | **hexound** | [![hexound](https://ag.hexor.cy/api/badge?name=hexound&revision=true)](https://ag.hexor.cy/applications/argocd/hexound) |
@@ -62,9 +65,12 @@ ArgoCD homelab project
 | **sonarr-stack** | [![sonarr-stack](https://ag.hexor.cy/api/badge?name=sonarr-stack&revision=true)](https://ag.hexor.cy/applications/argocd/sonarr-stack) |
 | **stirling-pdf** | [![stirling-pdf](https://ag.hexor.cy/api/badge?name=stirling-pdf&revision=true)](https://ag.hexor.cy/applications/argocd/stirling-pdf) |
 | **syncthing** | [![syncthing](https://ag.hexor.cy/api/badge?name=syncthing&revision=true)](https://ag.hexor.cy/applications/argocd/syncthing) |
+| **teamspeak** | [![teamspeak](https://ag.hexor.cy/api/badge?name=teamspeak&revision=true)](https://ag.hexor.cy/applications/argocd/teamspeak) |
 | **tg-bots** | [![tg-bots](https://ag.hexor.cy/api/badge?name=tg-bots&revision=true)](https://ag.hexor.cy/applications/argocd/tg-bots) |
 | **vaultwarden** | [![vaultwarden](https://ag.hexor.cy/api/badge?name=vaultwarden&revision=true)](https://ag.hexor.cy/applications/argocd/vaultwarden) |
 | **vpn** | [![vpn](https://ag.hexor.cy/api/badge?name=vpn&revision=true)](https://ag.hexor.cy/applications/argocd/vpn) |
+| **web-petting** | [![web-petting](https://ag.hexor.cy/api/badge?name=web-petting&revision=true)](https://ag.hexor.cy/applications/argocd/web-petting) |
+| **wedding** | [![wedding](https://ag.hexor.cy/api/badge?name=wedding&revision=true)](https://ag.hexor.cy/applications/argocd/wedding) |
 | **xandikos** | [![xandikos](https://ag.hexor.cy/api/badge?name=xandikos&revision=true)](https://ag.hexor.cy/applications/argocd/xandikos) |

 </td>
@@ -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
@@ -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"
@@ -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
@@ -0,0 +1,8 @@
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+
+resources:
+  - app.yaml
+  - configmap.yaml
+  - deployment.yaml
+  - 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
@@ -9,18 +9,18 @@ resources:
 helmCharts:
  - name: ollama
    repo: https://otwld.github.io/ollama-helm/
-    version: 1.49.0
+    version: 1.58.0
    releaseName: ollama
    namespace: ollama
    valuesFile: ollama-values.yaml
    includeCRDs: true
  - name: open-webui
    repo: https://helm.openwebui.com/
-    version: 12.10.0
+    version: 14.8.0
    releaseName: openweb-ui
    namespace: ollama
    valuesFile: openweb-ui-values.yaml
    includeCRDs: true

 patches:
-  - path: patch-runtimeclass.yaml
+  - path: patch-runtimeclass.yaml
@@ -31,7 +31,7 @@ ollama:
        - qwen3-vl:8b
        
 pipelines:
-  enabled: true
+  enabled: false
  nodeSelector:
    kubernetes.io/hostname: master.tail2fe2d.ts.net
  
@@ -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
@@ -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
Author	SHA1	Message	Date
Ultradesu	2bd3d91595	llama.cpp fixed DNS Auto-update README / Generate README and Create MR (push) Failing after 11m42s Details Check with kubeconform / lint (push) Failing after 12m48s Details Update Kubernetes Services Wiki / Generate and Update K8s Wiki (push) Failing after 13m55s Details	2026-06-04 18:47:10 +03:00
Ultradesu	6f1f6c349d	llama.cpp fixed model name Check with kubeconform / lint (push) Failing after 11m8s Details Update Kubernetes Services Wiki / Generate and Update K8s Wiki (push) Failing after 12m15s Details Auto-update README / Generate README and Create MR (push) Failing after 15m0s Details	2026-06-04 18:37:20 +03:00
Ultradesu	a8ee4bd2b2	pinned llama.cpp to server-rocm-b9501 Update Kubernetes Services Wiki / Generate and Update K8s Wiki (push) Successful in 11s Details Auto-update README / Generate README and Create MR (push) Failing after 13m24s Details Check with kubeconform / lint (push) Failing after 14m31s Details	2026-06-04 17:24:50 +03:00
Ultradesu	0018d2b418	pinned llama.cpp to server-rocm-b9501 Check with kubeconform / lint (push) Successful in 13s Details Auto-update README / Generate README and Create MR (push) Failing after 11m59s Details Update Kubernetes Services Wiki / Generate and Update K8s Wiki (push) Failing after 14m13s Details	2026-06-04 17:19:19 +03:00
Ultradesu	82dbe84075	Added llama.cpp on ai Auto-update README / Generate README and Create MR (push) Failing after 10m17s Details Check with kubeconform / lint (push) Failing after 11m23s Details Update Kubernetes Services Wiki / Generate and Update K8s Wiki (push) Failing after 12m29s Details	2026-06-04 16:59:58 +03:00
Ultradesu	6b717f5219	Added amd-gpu controller Check with kubeconform / lint (push) Successful in 33s Details Update Kubernetes Services Wiki / Generate and Update K8s Wiki (push) Failing after 11m48s Details Auto-update README / Generate README and Create MR (push) Failing after 14m2s Details	2026-06-04 16:46:49 +03:00
ab	0c1aa7d633	Merge pull request 'Auto-update README with k8s applications' (#406 ) from auto-update-readme-20260604-130654 into main Update Kubernetes Services Wiki / Generate and Update K8s Wiki (push) Failing after 13m12s Details Reviewed-on: #406	2026-06-04 13:43:51 +00:00
Gitea Actions Bot	f7c279a67a	Auto-update README with current k8s applications Keycloak Terraform / Terraform (pull_request) Successful in 13s Details Generated by CI/CD workflow on 2026-06-04 13:06:54 This PR updates the README.md file with the current list of applications found in the k8s/ directory structure.	2026-06-04 13:06:54 +00:00
Ultradesu	09e43ded52	Updated ollama & openwebui Update Kubernetes Services Wiki / Generate and Update K8s Wiki (push) Successful in 6s Details Check with kubeconform / lint (push) Successful in 5s Details Auto-update README / Generate README and Create MR (push) Successful in 6s Details	2026-06-04 16:06:30 +03:00