[CI] Move nightly-a2 test to hk (#5807)

### What this PR does / why we need it?
This patch initial testing involved connecting two nodes from the HK
region to nightly A2.

- vLLM version: v0.13.0
- vLLM main:
2f4e6548ef

---------

Signed-off-by: wangli <wangli858794774@gmail.com>

tests/e2e/nightly/multi_node/scripts/lws-a2.yaml.jinja2

@@ -0,0 +1,138 @@
+apiVersion: leaderworkerset.x-k8s.io/v1
+kind: LeaderWorkerSet
+metadata:
+  name: vllm
+  namespace: vllm-project
+spec:
+  replicas: {{ replicas | default(1) }}
+  leaderWorkerTemplate:
+    size: {{ size | default(2) }}
+    restartPolicy: None
+    leaderTemplate:
+      metadata:
+        labels:
+          role: leader
+      spec:
+        schedulerName: volcano
+        tolerations:
+          - key: "instance"
+            operator: "Equal"
+            value: "vllm"
+            effect: "NoSchedule"
+        containers:
+          - name: vllm-leader
+            imagePullPolicy: Always
+            image: {{ image | default("swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/vllm-ascend:nightly-a2") }}
+            env:
+              - name: CONFIG_YAML_PATH
+                value: {{ config_file_path | default("DeepSeek-V3.yaml") }}
+              - name: WORKSPACE
+                value: "/vllm-workspace"
+              - name: FAIL_TAG
+                value: {{ fail_tag | default("FAIL_TAG") }}
+            command:
+              - sh
+              - -c
+              - |
+                bash /root/.cache/tests/run.sh
+            resources:
+              limits:
+                huawei.com/ascend-1980: {{ npu_per_node | default("16") }}
+                memory: 512Gi
+                ephemeral-storage: 100Gi
+              requests:
+                huawei.com/ascend-1980: {{ npu_per_node | default("16") }}
+                ephemeral-storage: 100Gi
+                cpu: 125
+            ports:
+              - containerPort: 8080
+            # readinessProbe:
+            #   tcpSocket:
+            #     port: 8080
+            #   initialDelaySeconds: 15
+            #   periodSeconds: 10
+            volumeMounts:
+              - mountPath: /root/.cache
+                name: shared-volume
+              - mountPath: /usr/local/Ascend/driver/tools
+                name: driver-tools
+              - mountPath: /dev/shm
+                name: dshm
+        volumes:
+        - name: dshm
+          emptyDir:
+            medium: Memory
+            sizeLimit: 15Gi
+        - name: shared-volume
+          persistentVolumeClaim:
+            claimName: vllm-project-hk001
+        - name: driver-tools
+          hostPath:
+            path: /usr/local/Ascend/driver/tools
+    workerTemplate:
+      spec:
+        schedulerName: volcano
+        tolerations:
+          - key: "instance"
+            operator: "Equal"
+            value: "vllm"
+            effect: "NoSchedule"
+        containers:
+          - name: vllm-worker
+            imagePullPolicy: Always
+            image: {{ image | default("swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/vllm-ascend:nightly-a2") }}
+            env:
+              - name: CONFIG_YAML_PATH
+                value: {{ config_file_path | default("DeepSeek-V3.yaml") }}
+              - name: WORKSPACE
+                value: "/vllm-workspace"
+              - name: FAIL_TAG
+                value: {{ fail_tag | default("FAIL_TAG") }}
+            command:
+              - sh
+              - -c
+              - |
+                bash /root/.cache/tests/run.sh
+            resources:
+              limits:
+                huawei.com/ascend-1980: {{ npu_per_node | default("16") }}
+                memory: 512Gi
+                ephemeral-storage: 100Gi
+              requests:
+                huawei.com/ascend-1980: {{ npu_per_node | default("16") }}
+                ephemeral-storage: 100Gi
+                cpu: 125
+            volumeMounts:
+              - mountPath: /root/.cache
+                name: shared-volume
+              - mountPath: /usr/local/Ascend/driver/tools
+                name: driver-tools
+              - mountPath: /dev/shm
+                name: dshm
+        volumes:
+        - name: dshm
+          emptyDir:
+            medium: Memory
+            sizeLimit: 15Gi
+        - name: shared-volume
+          persistentVolumeClaim:
+            claimName: vllm-project-hk001
+        - name: driver-tools
+          hostPath:
+            path: /usr/local/Ascend/driver/tools
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: vllm-leader
+  namespace: vllm-project
+spec:
+  ports:
+    - name: http
+      port: 8080
+      protocol: TCP
+      targetPort: 8080
+  selector:
+    leaderworkerset.sigs.k8s.io/name: vllm
+    role: leader
+  type: ClusterIP

tests/e2e/nightly/multi_node/scripts/lws.yaml.jinja2

@@ -22,13 +22,6 @@ spec:
                 value: {{ config_file_path | default("DeepSeek-V3.yaml") }}
               - name: WORKSPACE
                 value: "/vllm-workspace"
-              # Set vLLM version and vLLM-Ascend version here, once there is a new release, update here.
-              - name: VLLM_ASCEND_VERSION
-                value: {{ vllm_ascend_ref | default("main") }}
-              - name: VLLM_ASCEND_REMOTE_URL
-                value: {{ vllm_ascend_remote_url | default("https://github.com/vllm-project/vllm-ascend.git") }}
-              - name: RESULT_FILE_PATH
-                value: {{ result_file_path | default("/root/.cache/tests/ret") }}
               - name: FAIL_TAG
                 value: {{ fail_tag | default("FAIL_TAG") }}
             command:
@@ -81,13 +74,6 @@ spec:
                 value: {{ config_file_path | default("DeepSeek-V3.yaml") }}
               - name: WORKSPACE
                 value: "/vllm-workspace"
-              # Set vLLM version and vLLM-Ascend version here, once there is a new release, update here.
-              - name: VLLM_ASCEND_VERSION
-                value: {{ vllm_ascend_ref | default("main") }}
-              - name: VLLM_ASCEND_REMOTE_URL
-                value: {{ vllm_ascend_remote_url | default("https://github.com/vllm-project/vllm-ascend.git") }}
-              - name: RESULT_FILE_PATH
-                value: {{ result_file_path | default("/root/.cache/tests/ret") }}
               - name: FAIL_TAG
                 value: {{ fail_tag | default("FAIL_TAG") }}
             command:

tests/e2e/nightly/multi_node/scripts/run.sh

@@ -167,8 +167,8 @@ run_tests_with_log() {
         if [ $ret -eq 0 ]; then
             print_success "All tests passed!"
         else
-            print_failure "Some tests failed, please check the error stack above for details.\
-            If this is insufficient to pinpoint the error, please download and review the logs of all other nodes from the job's summary."
+            print_failure "Some tests failed, please check the error stack above for details. \
+If this is insufficient to pinpoint the error, please download and review the logs of all other nodes from the job's summary."
         fi
     fi
 }