search

allenporter / k8s-gitops

Flux/Gitops managed k8s cluster
32 stars 1 forks source link

Remove llama clblast #1864

Closed allenporter closed 1 month ago

github-actions[bot] commented 1 month ago 
--- kubernetes/ml/prod Kustomization: flux-system/ml HelmRelease: llama/llama-clblast

+++ kubernetes/ml/prod Kustomization: flux-system/ml HelmRelease: llama/llama-clblast

@@ -1,93 +0,0 @@

----
-apiVersion: helm.toolkit.fluxcd.io/v2beta1
-kind: HelmRelease
-metadata:
-  labels:
-    kustomize.toolkit.fluxcd.io/name: ml
-    kustomize.toolkit.fluxcd.io/namespace: flux-system
-  name: llama-clblast
-  namespace: llama
-spec:
-  chart:
-    spec:
-      chart: app-template
-      interval: 30m
-      sourceRef:
-        kind: HelmRepository
-        name: bjw-s-helm-charts
-        namespace: flux-system
-      version: 2.4.0
-  install:
-    remediation:
-      retries: 3
-  interval: 5m
-  releaseName: llama-clblast
-  test:
-    enable: false
-  values:
-    controllers:
-      main:
-        containers:
-          main:
-            env:
-            - name: MODEL_DIR
-              value: /data/models
-            - name: CONFIG_FILE
-              value: /config/model-config.json
-            image:
-              pullPolicy: IfNotPresent
-              repository: ghcr.io/allenporter/llama-cpp-server-clblast
-              tag: v2.16.0
-        initContainers:
-          download-model:
-            env:
-            - name: MODEL_DIR
-              value: /data/models
-            - name: MODEL_URLS
-              value: https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.1-GGUF/resolve/main/mistral-7b-instruct-v0.1.Q4_K_M.gguf,https://huggingface.co/chanwit/flux-7b-v0.1-gguf/resolve/main/flux-7b-v0.1-Q4_K_M.gguf,https://huggingface.co/meetkai/functionary-7b-v1.4-GGUF/resolve/main/functionary-7b-v1.4.q4_0.gguf,https://huggingface.co/TheBloke/deepseek-coder-6.7B-instruct-GGUF/resolve/main/deepseek-coder-6.7b-instruct.Q4_K_M.gguf
-            image:
-              pullPolicy: IfNotPresent
-              repository: ghcr.io/allenporter/llama-cpp-server-model-fetch
-              tag: v2.16.0
-        strategy: Recreate
-    ingress:
-      main:
-        annotations:
-          cert-manager.io/cluster-issuer: letsencrypt
-        enabled: true
-        hosts:
-        - host: llama-clblast.k8s.mrv.thebends.org
-          paths:
-          - path: /
-            service:
-              name: main
-              port: http
-        tls:
-        - hosts:
-          - llama-clblast.k8s.mrv.thebends.org
-          secretName: llama-clblast-tls
-    persistence:
-      config:
-        enabled: true
-        globalMounts:
-        - path: /config/model-config.json
-          readOnly: true
-          subPath: model-config.json
-        name: clblast-model-config-m5fm4kc97t
-        type: configMap
-      data:
-        accessMode: ReadWriteOnce
-        enabled: true
-        globalMounts:
-        - path: /data
-          readOnly: false
-        retain: true
-        size: 40Gi
-        storageClassName: local-hostpath
-        type: persistentVolumeClaim
-    service:
-      main:
-        ports:
-          http:
-            port: 8000
-
--- kubernetes/ml/prod Kustomization: flux-system/ml ConfigMap: llama/clblast-model-config-m5fm4kc97t

+++ kubernetes/ml/prod Kustomization: flux-system/ml ConfigMap: llama/clblast-model-config-m5fm4kc97t

@@ -1,54 +0,0 @@

----
-apiVersion: v1
-data:
-  model-config.json: |
-    {
-      "host": "0.0.0.0",
-      "port": 8080,
-      "models": [
-        {
-          "model": "/data/models/mistral-7b-instruct-v0.1.Q4_K_M.gguf",
-          "model_alias": "gpt-3.5-turbo",
-          "chat_format": "llama-2",
-          "n_gpu_layers": 35,
-          "offload_kqv": true,
-          "n_ctx": 4096,
-          "use_mlock": false
-        },
-        {
-          "model": "/data/models/flux-7b-v0.1-Q4_K_M.gguf",
-          "model_alias": "flux-7b",
-          "chat_format": "zephyr",
-          "n_gpu_layers": 35,
-          "offload_kqv": true,
-          "n_ctx": 4096,
-          "use_mlock": false
-        },
-        {
-          "model": "/data/models/functionary-7b-v1.4.q4_0.gguf",
-          "model_alias": "functionary-7b",
-          "chat_format": "functionary",
-          "n_gpu_layers": 35,
-          "offload_kqv": true,
-          "n_ctx": 4096,
-          "use_mlock": false
-        },
-        {
-          "model": "/data/models/deepseek-coder-6.7b-instruct.Q4_K_M.gguf",
-          "model_alias": "deepseek-coder-6.7b-instruct",
-          "chat_format": "snoozy",
-          "n_gpu_layers": 35,
-          "offload_kqv": true,
-          "n_ctx": 4096,
-          "use_mlock": false
-        }
-      ]
-    }
-kind: ConfigMap
-metadata:
-  labels:
-    kustomize.toolkit.fluxcd.io/name: ml
-    kustomize.toolkit.fluxcd.io/namespace: flux-system
-  name: clblast-model-config-m5fm4kc97t
-  namespace: llama
-
--- kubernetes/ml/prod Kustomization: flux-system/ml HelmRelease: llama/llama-gpt-ui-clblast

+++ kubernetes/ml/prod Kustomization: flux-system/ml HelmRelease: llama/llama-gpt-ui-clblast

@@ -1,63 +0,0 @@

----
-apiVersion: helm.toolkit.fluxcd.io/v2beta1
-kind: HelmRelease
-metadata:
-  labels:
-    kustomize.toolkit.fluxcd.io/name: ml
-    kustomize.toolkit.fluxcd.io/namespace: flux-system
-  name: llama-gpt-ui-clblast
-  namespace: llama
-spec:
-  chart:
-    spec:
-      chart: app-template
-      interval: 30m
-      sourceRef:
-        kind: HelmRepository
-        name: bjw-s-helm-charts
-        namespace: flux-system
-      version: 2.4.0
-  install:
-    remediation:
-      retries: 3
-  interval: 5m
-  releaseName: llama-gpt-ui-clblast
-  test:
-    enable: false
-  values:
-    controllers:
-      main:
-        containers:
-          main:
-            env:
-            - name: OPENAI_API_HOST
-              value: http://llama-clblast:8000
-            - name: OPENAI_API_KEY
-              value: sk-XXXXXXXXXXXXXXXXXXXX
-            image:
-              pullPolicy: IfNotPresent
-              repository: ghcr.io/allenporter/llama-gpt-ui
-              tag: v0.1.1
-        strategy: Recreate
-    ingress:
-      main:
-        annotations:
-          cert-manager.io/cluster-issuer: letsencrypt
-        enabled: true
-        hosts:
-        - host: llama-gpt-clblast.k8s.mrv.thebends.org
-          paths:
-          - path: /
-            service:
-              name: main
-              port: http
-        tls:
-        - hosts:
-          - llama-gpt-clblast.k8s.mrv.thebends.org
-          secretName: llama-gpt-clblast-tls
-    service:
-      main:
-        ports:
-          http:
-            port: 3000
-
github-actions[bot] commented 1 month ago 
--- HelmRelease: llama/llama-gpt-ui-clblast Service: llama/llama-gpt-ui-clblast

+++ HelmRelease: llama/llama-gpt-ui-clblast Service: llama/llama-gpt-ui-clblast

@@ -1,22 +0,0 @@

----
-apiVersion: v1
-kind: Service
-metadata:
-  name: llama-gpt-ui-clblast
-  labels:
-    app.kubernetes.io/instance: llama-gpt-ui-clblast
-    app.kubernetes.io/managed-by: Helm
-    app.kubernetes.io/name: llama-gpt-ui-clblast
-    app.kubernetes.io/service: llama-gpt-ui-clblast
-spec:
-  type: ClusterIP
-  ports:
-  - port: 3000
-    targetPort: 3000
-    protocol: TCP
-    name: http
-  selector:
-    app.kubernetes.io/component: main
-    app.kubernetes.io/instance: llama-gpt-ui-clblast
-    app.kubernetes.io/name: llama-gpt-ui-clblast
-
--- HelmRelease: llama/llama-gpt-ui-clblast Deployment: llama/llama-gpt-ui-clblast

+++ HelmRelease: llama/llama-gpt-ui-clblast Deployment: llama/llama-gpt-ui-clblast

@@ -1,65 +0,0 @@

----
-apiVersion: apps/v1
-kind: Deployment
-metadata:
-  name: llama-gpt-ui-clblast
-  labels:
-    app.kubernetes.io/component: main
-    app.kubernetes.io/instance: llama-gpt-ui-clblast
-    app.kubernetes.io/managed-by: Helm
-    app.kubernetes.io/name: llama-gpt-ui-clblast
-spec:
-  revisionHistoryLimit: 3
-  replicas: 1
-  strategy:
-    type: Recreate
-  selector:
-    matchLabels:
-      app.kubernetes.io/component: main
-      app.kubernetes.io/name: llama-gpt-ui-clblast
-      app.kubernetes.io/instance: llama-gpt-ui-clblast
-  template:
-    metadata:
-      labels:
-        app.kubernetes.io/component: main
-        app.kubernetes.io/instance: llama-gpt-ui-clblast
-        app.kubernetes.io/name: llama-gpt-ui-clblast
-    spec:
-      enableServiceLinks: true
-      serviceAccountName: default
-      automountServiceAccountToken: true
-      hostIPC: false
-      hostNetwork: false
-      hostPID: false
-      dnsPolicy: ClusterFirst
-      containers:
-      - env:
-        - name: OPENAI_API_HOST
-          value: http://llama-clblast:8000
-        - name: OPENAI_API_KEY
-          value: sk-XXXXXXXXXXXXXXXXXXXX
-        image: ghcr.io/allenporter/llama-gpt-ui:v0.1.1
-        imagePullPolicy: IfNotPresent
-        livenessProbe:
-          failureThreshold: 3
-          initialDelaySeconds: 0
-          periodSeconds: 10
-          tcpSocket:
-            port: 3000
-          timeoutSeconds: 1
-        name: main
-        readinessProbe:
-          failureThreshold: 3
-          initialDelaySeconds: 0
-          periodSeconds: 10
-          tcpSocket:
-            port: 3000
-          timeoutSeconds: 1
-        startupProbe:
-          failureThreshold: 30
-          initialDelaySeconds: 0
-          periodSeconds: 5
-          tcpSocket:
-            port: 3000
-          timeoutSeconds: 1
-
--- HelmRelease: llama/llama-gpt-ui-clblast Ingress: llama/llama-gpt-ui-clblast

+++ HelmRelease: llama/llama-gpt-ui-clblast Ingress: llama/llama-gpt-ui-clblast

@@ -1,28 +0,0 @@

----
-apiVersion: networking.k8s.io/v1
-kind: Ingress
-metadata:
-  name: llama-gpt-ui-clblast
-  labels:
-    app.kubernetes.io/instance: llama-gpt-ui-clblast
-    app.kubernetes.io/managed-by: Helm
-    app.kubernetes.io/name: llama-gpt-ui-clblast
-  annotations:
-    cert-manager.io/cluster-issuer: letsencrypt
-spec:
-  tls:
-  - hosts:
-    - llama-gpt-clblast.k8s.mrv.thebends.org
-    secretName: llama-gpt-clblast-tls
-  rules:
-  - host: llama-gpt-clblast.k8s.mrv.thebends.org
-    http:
-      paths:
-      - path: /
-        pathType: Prefix
-        backend:
-          service:
-            name: llama-gpt-ui-clblast
-            port:
-              number: 3000
-
--- HelmRelease: llama/llama-clblast PersistentVolumeClaim: llama/llama-clblast-data

+++ HelmRelease: llama/llama-clblast PersistentVolumeClaim: llama/llama-clblast-data

@@ -1,18 +0,0 @@

----
-kind: PersistentVolumeClaim
-apiVersion: v1
-metadata:
-  name: llama-clblast-data
-  labels:
-    app.kubernetes.io/instance: llama-clblast
-    app.kubernetes.io/managed-by: Helm
-    app.kubernetes.io/name: llama-clblast
-  annotations:
-    helm.sh/resource-policy: keep
-spec:
-  accessModes:
-  - ReadWriteOnce
-  resources:
-    requests:
-      storage: 40Gi
-
--- HelmRelease: llama/llama-clblast Service: llama/llama-clblast

+++ HelmRelease: llama/llama-clblast Service: llama/llama-clblast

@@ -1,22 +0,0 @@

----
-apiVersion: v1
-kind: Service
-metadata:
-  name: llama-clblast
-  labels:
-    app.kubernetes.io/instance: llama-clblast
-    app.kubernetes.io/managed-by: Helm
-    app.kubernetes.io/name: llama-clblast
-    app.kubernetes.io/service: llama-clblast
-spec:
-  type: ClusterIP
-  ports:
-  - port: 8000
-    targetPort: 8000
-    protocol: TCP
-    name: http
-  selector:
-    app.kubernetes.io/component: main
-    app.kubernetes.io/instance: llama-clblast
-    app.kubernetes.io/name: llama-clblast
-
--- HelmRelease: llama/llama-clblast Deployment: llama/llama-clblast

+++ HelmRelease: llama/llama-clblast Deployment: llama/llama-clblast

@@ -1,95 +0,0 @@

----
-apiVersion: apps/v1
-kind: Deployment
-metadata:
-  name: llama-clblast
-  labels:
-    app.kubernetes.io/component: main
-    app.kubernetes.io/instance: llama-clblast
-    app.kubernetes.io/managed-by: Helm
-    app.kubernetes.io/name: llama-clblast
-spec:
-  revisionHistoryLimit: 3
-  replicas: 1
-  strategy:
-    type: Recreate
-  selector:
-    matchLabels:
-      app.kubernetes.io/component: main
-      app.kubernetes.io/name: llama-clblast
-      app.kubernetes.io/instance: llama-clblast
-  template:
-    metadata:
-      labels:
-        app.kubernetes.io/component: main
-        app.kubernetes.io/instance: llama-clblast
-        app.kubernetes.io/name: llama-clblast
-    spec:
-      enableServiceLinks: true
-      serviceAccountName: default
-      automountServiceAccountToken: true
-      hostIPC: false
-      hostNetwork: false
-      hostPID: false
-      dnsPolicy: ClusterFirst
-      initContainers:
-      - env:
-        - name: MODEL_DIR
-          value: /data/models
-        - name: MODEL_URLS
-          value: https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.1-GGUF/resolve/main/mistral-7b-instruct-v0.1.Q4_K_M.gguf,https://huggingface.co/chanwit/flux-7b-v0.1-gguf/resolve/main/flux-7b-v0.1-Q4_K_M.gguf,https://huggingface.co/meetkai/functionary-7b-v1.4-GGUF/resolve/main/functionary-7b-v1.4.q4_0.gguf,https://huggingface.co/TheBloke/deepseek-coder-6.7B-instruct-GGUF/resolve/main/deepseek-coder-6.7b-instruct.Q4_K_M.gguf
-        image: ghcr.io/allenporter/llama-cpp-server-model-fetch:v2.16.0
-        imagePullPolicy: IfNotPresent
-        name: download-model
-        volumeMounts:
-        - mountPath: /config/model-config.json
-          name: config
-          readOnly: true
-          subPath: model-config.json
-        - mountPath: /data
-          name: data
-      containers:
-      - env:
-        - name: MODEL_DIR
-          value: /data/models
-        - name: CONFIG_FILE
-          value: /config/model-config.json
-        image: ghcr.io/allenporter/llama-cpp-server-clblast:v2.16.0
-        imagePullPolicy: IfNotPresent
-        livenessProbe:
-          failureThreshold: 3
-          initialDelaySeconds: 0
-          periodSeconds: 10
-          tcpSocket:
-            port: 8000
-          timeoutSeconds: 1
-        name: main
-        readinessProbe:
-          failureThreshold: 3
-          initialDelaySeconds: 0
-          periodSeconds: 10
-          tcpSocket:
-            port: 8000
-          timeoutSeconds: 1
-        startupProbe:
-          failureThreshold: 30
-          initialDelaySeconds: 0
-          periodSeconds: 5
-          tcpSocket:
-            port: 8000
-          timeoutSeconds: 1
-        volumeMounts:
-        - mountPath: /config/model-config.json
-          name: config
-          readOnly: true
-          subPath: model-config.json
-        - mountPath: /data
-          name: data
-      volumes:
-      - configMap:
-          name: clblast-model-config-m5fm4kc97t
-        name: config
-      - name: data
-        persistentVolumeClaim:
-          claimName: llama-clblast-data
-
--- HelmRelease: llama/llama-clblast Ingress: llama/llama-clblast

+++ HelmRelease: llama/llama-clblast Ingress: llama/llama-clblast

@@ -1,28 +0,0 @@

----
-apiVersion: networking.k8s.io/v1
-kind: Ingress
-metadata:
-  name: llama-clblast
-  labels:
-    app.kubernetes.io/instance: llama-clblast
-    app.kubernetes.io/managed-by: Helm
-    app.kubernetes.io/name: llama-clblast
-  annotations:
-    cert-manager.io/cluster-issuer: letsencrypt
-spec:
-  tls:
-  - hosts:
-    - llama-clblast.k8s.mrv.thebends.org
-    secretName: llama-clblast-tls
-  rules:
-  - host: llama-clblast.k8s.mrv.thebends.org
-    http:
-      paths:
-      - path: /
-        pathType: Prefix
-        backend:
-          service:
-            name: llama-clblast
-            port:
-              number: 8000
-