openclaw: move mvp inference to titan-24

services/openclaw/deployment.yaml

@@ -20,7 +20,7 @@ spec:
         app: openclaw
       annotations:
         ai.bstein.dev/role: testing-triage
-        ai.bstein.dev/placement: Jetson MVP lane (titan-21)
+        ai.bstein.dev/placement: accelerator MVP lane (titan-24)
     spec:
       serviceAccountName: openclaw-triage
       automountServiceAccountToken: true
@@ -36,7 +36,7 @@ spec:
                   - key: kubernetes.io/hostname
                     operator: In
                     values:
-                      - titan-21
+                      - titan-24
       initContainers:
         - name: init-config
           image: busybox:1.37
@@ -86,7 +86,7 @@ spec:
               memory: 64Mi
       containers:
         - name: gateway
-          image: ghcr.io/openclaw/openclaw:slim@sha256:ca134367c291b982ec301038af4602f397c7f90cc6c6d263c12a78a5fe1bde57
+          image: ghcr.io/openclaw/openclaw:slim@sha256:5ea30d02a706c49795ed0a3c1526dec51ed90107a6859e93bf27a663105d1c28
           imagePullPolicy: IfNotPresent
           command:
             - node

services/openclaw/ollama-deployment.yaml

@@ -20,7 +20,7 @@ spec:
         app: openclaw-ollama
       annotations:
         ai.bstein.dev/model: qwen2.5:1.5b-instruct-q4_0
-        ai.bstein.dev/gpu: Jetson MVP lane (titan-21)
+        ai.bstein.dev/gpu: accelerator MVP lane (titan-24)
     spec:
       runtimeClassName: nvidia
       affinity:
@@ -31,7 +31,7 @@ spec:
                   - key: kubernetes.io/hostname
                     operator: In
                     values:
-                      - titan-21
+                      - titan-24
       volumes:
         - name: models
           emptyDir: {}
@@ -68,8 +68,8 @@ spec:
               memory: 4Gi
               nvidia.com/gpu.shared: 1
             limits:
-              cpu: "3"
+              cpu: "4"
-              memory: 8Gi
+              memory: 10Gi
               nvidia.com/gpu.shared: 1
       containers:
         - name: ollama
@@ -101,10 +101,10 @@ spec:
             timeoutSeconds: 5
           resources:
             requests:
-              cpu: "1"
+              cpu: "2"
               memory: 8Gi
               nvidia.com/gpu.shared: 1
             limits:
-              cpu: "3"
+              cpu: "6"
-              memory: 10Gi
+              memory: 12Gi
               nvidia.com/gpu.shared: 1