refactor(k8s): Reorganize into 5-layer structure with production kustomizations

2026-08-18 15:08:01 -07:00
parent 563f720d09
commit 0f30d77288
214 changed files with 405 additions and 885 deletions
@@ -0,0 +1,40 @@
+replicaCount: 1
+
+image:
+  repository: ollama/ollama
+  pullPolicy: IfNotPresent
+  tag: "latest"
+
+service:
+  type: ClusterIP
+  port: 11434
+
+resources:
+  requests:
+    cpu: 8
+    memory: 60Gi
+  limits:
+    cpu: 16
+    memory: 100Gi
+
+pvc:
+  enabled: true
+  size: 115Gi
+  storageClassName: longhorn-llm
+
+nodeAffinity:
+  zone: az-a
+
+env:
+  OLLAMA_MODELS: /root/.ollama/models
+  OLLAMA_MAX_LOADED_MODELS: "2"
+  OLLAMA_NUM_PARALLEL: "2"
+  OLLAMA_MAX_QUEUE: "64"
+  OLLAMA_KEEP_ALIVE: "-1"
+  OLLAMA_HOST: "0.0.0.0:11434"
+
+preloadJob:
+  enabled: false
+  hotModels:
+    - ornith:35b
+    - deepseek-r1:70b