add model svc yamls

Signed-off-by: Ning Wang <[email protected]>

Author: nwangfw

test/regression/v0.4.0/sglang/32b-service.yaml

@@ -0,0 +1,14 @@
+apiVersion: v1
+kind: Service
+metadata:
+  name: qwen3-32b-service
+  namespace: default
+spec:
+  selector:
+    model.aibrix.ai/name: qwen3-32b
+  ports:
+    - protocol: TCP
+      port: 8000
+      targetPort: 8000
+      nodePort: 30009
+  type: NodePort

test/regression/v0.4.0/sglang/8b-service.yaml

@@ -0,0 +1,37 @@
+apiVersion: v1
+kind: Service
+metadata:
+  name: qwen3-8b-service
+  namespace: default
+spec:
+  selector:
+    model.aibrix.ai/name: qwen3-8b
+  ports:
+    - protocol: TCP
+      port: 8000
+      targetPort: 8000
+      nodePort: 30008  
+  type: NodePort
+
+
+apiVersion: v1
+kind: Service
+metadata:
+  name: llama2-7b
+  namespace: default
+  labels:
+    prometheus-discovery: "true"
+  annotations:
+    prometheus.io/scrape: "true"
+    prometheus.io/path: "/metrics"
+    prometheus.io/port: "8000"
+spec:
+  selector:
+    model.aibrix.ai/name: "llama2-7b"
+  ports:
+    - protocol: TCP
+      name: metrics
+      port: 8000
+      targetPort: 8000
+      nodePort: 30081
+  type: NodePort

test/regression/v0.4.0/vllm/8b-service.yaml

@@ -0,0 +1,14 @@
+apiVersion: v1
+kind: Service
+metadata:
+  name: qwen3-8b-service
+  namespace: default
+spec:
+  selector:
+    model.aibrix.ai/name: qwen3-8b
+  ports:
+    - protocol: TCP
+      port: 8000
+      targetPort: 8000
+      nodePort: 30008
+  type: NodePort

test/regression/v0.4.0/vllm/vllm-base.yaml

@@ -7,7 +7,7 @@ metadata:
   name: qwen3-8b
   namespace: default
 spec:
-  replicas: 1
+  replicas: 2
   selector:
     matchLabels:
       model.aibrix.ai/name: qwen3-8b