Fix envoy, gateway, and quickstart pd-model images (#1812)

Signed-off-by: Dengcheng Zhu <dengcheng.zhu@gmail.com>

Author: dczhu

dist/chart/vke.yaml

@@ -116,7 +116,7 @@ gateway:
                     - "true"
     container:
       envoy:
-        image: aibrix-public-release-cn-beijing.cr.volces.com/envoyproxy/envoy:v1.33.2
+        image: aibrix-public-release-cn-beijing.cr.volces.com/aibrix/envoy:v1.33.2
         resources:
           requests:
             cpu: "1"
@@ -125,7 +125,7 @@ gateway:
             cpu: "1"
             memory: 1Gi
       shutdownManager:
-        image: aibrix-public-release-cn-beijing.cr.volces.com/envoyproxy/gateway:v1.2.8
+        image: aibrix-public-release-cn-beijing.cr.volces.com/aibrix/gateway:v1.2.8
         resources:
           requests:
             cpu: 10m

samples/quickstart/vke/pd-model.yaml

@@ -28,7 +28,7 @@ spec:
             spec:
               containers:
                 - name: prefill
-                  image: aibrix-public-release-cn-beijing.cr.volces.com/aibrix/vllm-openai:0.11.0-cu128-nixl-v0.4.1
+                  image: aibrix-public-release-cn-beijing.cr.volces.com/aibrix/vllm-openai:v0.10.2-aibrix-v0.5.0-nixl-0.7.1-20251123
                   command: ["sh", "-c"]
                   args:
                     - |
@@ -84,7 +84,7 @@ spec:
             spec:
               containers:
                 - name: decode
-                  image: aibrix-public-release-cn-beijing.cr.volces.com/aibrix/vllm-openai:0.11.0-cu128-nixl-v0.4.1
+                  image: aibrix-public-release-cn-beijing.cr.volces.com/aibrix/vllm-openai:v0.10.2-aibrix-v0.5.0-nixl-0.7.1-20251123
                   command: ["sh", "-c"]
                   args:
                     - |
@@ -136,4 +136,4 @@ spec:
                 - name: model-hostpath
                   hostPath:
                     path: /root/models
-                    type: DirectoryOrCreate
+                    type: DirectoryOrCreate