feat(supabase): add services and statefulset for database management

feat(synapse): update ingress to use traefik ingress class and bump version

feat(syncthing-discovery): introduce syncthing discovery service with deployment and ingress

feat(syncthing-relay): add syncthing relay server with deployment and ingress configuration

fix(taiga): update liveness and readiness probes to use tcpSocket for health checks

fix(taiga): change PVC access mode to ReadWriteMany for media and static storage

feat(traefik): add icon and ignore rules for traefik service

docs(ushahidi): add notes for Redis configuration and Laravel startup probe adjustments

feat(ushahidi): implement dedicated Redis deployment for Ushahidi

fix(vllm): update deployment strategy and readiness/liveness probes for improved stability

fix(writefreely): pin writefreely image version to v0.15.1 for consistency

docs(zulip): add notes for TLS-terminating reverse proxy configuration and expected behavior

vllm/versions/0/deployment.yaml

@@ -4,6 +4,8 @@ metadata:
   name: vllm
 spec:
   replicas: 1
+  strategy:
+    type: Recreate
   selector:
     matchLabels:
       component: inference
@@ -12,14 +14,13 @@ spec:
       labels:
         component: inference
     spec:
+      runtimeClassName: nvidia
+      enableServiceLinks: false
       securityContext:
-        runAsNonRoot: true
-        runAsUser: 1000
-        runAsGroup: 1000
         seccompProfile:
           type: RuntimeDefault
       nodeSelector:
-        nvidia.com/gpu.product: "{{ .gpuProduct }}"
+        feature.node.kubernetes.io/pci-0300_10de.present: "true"
       containers:
         - name: vllm
           image: vllm/vllm-openai:v0.5.4
@@ -29,18 +30,27 @@ spec:
             capabilities:
               drop:
               - ALL
-            readOnlyRootFilesystem: false
           args:
             - --model={{ .model }}
             - --max-model-len={{ .maxModelLen }}
             - --tensor-parallel-size=1
             - --gpu-memory-utilization={{ .gpuMemoryUtilization }}
-            - --enforce-eager=True
+            - --enforce-eager
+            - --api-key=$(VLLM_API_KEY)
           env:
+            - name: VLLM_API_KEY
+              valueFrom:
+                secretKeyRef:
+                  name: vllm-secrets
+                  key: apiKey
             - name: VLLM_TORCH_DTYPE
               value: "auto"
             - name: VLLM_WORKER_CONCURRENCY
               value: "1"
+            - name: HF_HOME
+              value: "/root/.cache/huggingface"
+            - name: NUMBA_CACHE_DIR
+              value: "/tmp"
           ports:
             - name: http
               containerPort: 8000
@@ -55,19 +65,21 @@ spec:
               nvidia.com/gpu: {{ .gpuCount }}
           readinessProbe:
             httpGet:
-              path: /v1/models
+              path: /health
               port: http
-            initialDelaySeconds: 30
-            periodSeconds: 10
-            timeoutSeconds: 5
+            initialDelaySeconds: 300
+            periodSeconds: 30
+            timeoutSeconds: 10
+            failureThreshold: 5
           livenessProbe:
             httpGet:
               path: /health
               port: http
-            initialDelaySeconds: 60
-            periodSeconds: 15
-            timeoutSeconds: 5
+            initialDelaySeconds: 600
+            periodSeconds: 60
+            timeoutSeconds: 10
+            failureThreshold: 3
       tolerations:
         - key: "nvidia.com/gpu"
           operator: "Exists"
-          effect: "NoSchedule"
+          effect: "NoSchedule"