fix(rtx6000-scaling): set minReplicas to 1 to prevent transient scale-up/down thrashing from periodic health checks

Prevents the watcher cron (every 5m) from causing unnecessary spot pod churn. Keeps 1 ready pod always (KEDA overrides deployment replicas).

infrastructure/gpus/base/keda-gpu-scaling/keda-vllm.yaml

@@ -13,6 +13,6 @@ spec:
     service: rtx6000-brain-service
     port: 8000
   replicas:
-    min: 0
+    min: 1
     max: 1