adjust the gpu deployment to increase max batch size

Author: ahg-g

config/manifests/vllm/gpu-deployment.yaml

@@ -24,6 +24,10 @@ spec:
           - "1"
           - "--port"
           - "8000"
+          - "--max-num-seq"
+          - "2048"
+          - "--compilation-config"
+          - "3"
           - "--enable-lora"
           - "--max-loras"
           - "2"