diff --git a/infrastructure/gpus/base/keda-gpu-scaling/keda-a100.yaml b/infrastructure/gpus/base/keda-gpu-scaling/keda-a100.yaml
index 08ed523..88d2367 100644
--- a/infrastructure/gpus/base/keda-gpu-scaling/keda-a100.yaml
+++ b/infrastructure/gpus/base/keda-gpu-scaling/keda-a100.yaml
@@ -5,15 +5,14 @@ metadata:
   namespace: customer1
 spec:
   hosts:
-    - a100-vllm.internal.cluster # Replace with actual internal routing host if needed
+  - a100-vllm.internal.cluster
   scaleTargetRef:
     name: openclaw-brain-vllm
     kind: Deployment
     apiVersion: apps/v1
     service: openclaw-brain-service
     port: 8000
-
   replicas:
     min: 0
     max: 1
-  scaledownPeriod: 900 # 15 minutes of idle time before scaling to zero
+  pollingInterval: 10
diff --git a/infrastructure/gpus/base/keda-gpu-scaling/keda-vllm.yaml b/infrastructure/gpus/base/keda-gpu-scaling/keda-vllm.yaml
index a26d73f..b29df7c 100644
--- a/infrastructure/gpus/base/keda-gpu-scaling/keda-vllm.yaml
+++ b/infrastructure/gpus/base/keda-gpu-scaling/keda-vllm.yaml
@@ -12,10 +12,7 @@ spec:
     apiVersion: apps/v1
     service: rtx6000-brain-service
     port: 8000
-
   replicas:
     min: 0
     max: 1
   pollingInterval: 10
-  cooldownPeriod: 30
-  scaledownPeriod: 900