feat: increase litellm resources (#144)

finding litellm performance has dropped, crashed in multiple cases, and
then it had scaled to the maximum level using the majority of memory in
cluster.

- reduce the rate at which litellm autoscales
- increase the requests/limits to match usage

Reviewed-on: #144

apps/base/litellm/hpa.yaml

@@ -10,14 +10,14 @@ spec:
     kind: Deployment
     name: litellm
   minReplicas: 2
-  maxReplicas: 10
+  maxReplicas: 4
   metrics:
     - type: Resource
       resource:
         name: cpu
         target:
           type: Utilization
-          averageUtilization: 60
+          averageUtilization: 80
   behavior:
     scaleUp:
       stabilizationWindowSeconds: 0
@@ -25,7 +25,7 @@ spec:
       policies:
         - type: Percent
           value: 100
-          periodSeconds: 30
+          periodSeconds: 60
         - type: Pods
           value: 4
           periodSeconds: 30
@@ -34,7 +34,7 @@ spec:
       selectPolicy: Min
       policies:
         - type: Percent
-          value: 10
+          value: 30
           periodSeconds: 60
         - type: Pods
           value: 2