[CI][Doc] Optimize multi-node CI (#3565)

### What this PR does / why we need it?
This pull request mainly do the following things:
1. Add a doc for multi-node CI, The main content is the mechanism
principle and how to contribute
2. Simplify the config yaml for more developer-friendly
3. Optimized the mooncake installation script to prevent accidental
failures during installation
4. Fix the workflow to ensure the kubernetes can be apply correctly
5. Add Qwen3-235B-W8A8 disaggregated_prefill test
6. Add GLM-4.5 multi dp test
7. Add 2p1d 4nodes disaggregated_prefill test
8. Refactor nightly tests
### Does this PR introduce _any_ user-facing change?

### How was this patch tested?


- vLLM version: v0.11.0rc3
- vLLM main:
17c540a993

---------

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

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

@@ -17,19 +17,24 @@ spec:
           - name: vllm-leader
             image: {{ image | default("m.daocloud.io/quay.io/ascend/cann:8.2.rc1-a3-ubuntu22.04-py3.11") }}
             env:
+              - name: CONFIG_YAML_PATH
+                value: {{ config_file_path | default("tests/e2e/nightly/multi_node/config/models/DeepSeek-V3.yaml") }}
               - name: WORKSPACE
                 value: "/root/workspace"
               # Set vLLM version and vLLM-Ascend version here, once there is a new release, update here.
               - name: VLLM_VERSION
                 value: "v0.11.0"
               - name: VLLM_ASCEND_VERSION
-                value: "main"
+                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/test_result.txt") }}
             command:
               - sh
               - -c
               - |
                 bash /root/.cache/tests/run.sh
-                tail -f /dev/null
             resources:
               limits:
                 huawei.com/ascend-1980: "16"
@@ -70,19 +75,24 @@ spec:
           - name: vllm-worker
             image: {{ image | default("m.daocloud.io/quay.io/ascend/cann:8.2.rc1-a3-ubuntu22.04-py3.11") }}
             env:
+              - name: CONFIG_YAML_PATH
+                value: {{ config_file_path | default("tests/e2e/nightly/multi_node/config/models/DeepSeek-V3.yaml") }}
               - name: WORKSPACE
                 value: "/root/workspace"
               # Set vLLM version and vLLM-Ascend version here, once there is a new release, update here.
               - name: VLLM_VERSION
                 value: "v0.11.0"
               - name: VLLM_ASCEND_VERSION
-                value: "main"
+                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/test_result.txt") }}
             command:
               - sh
               - -c
               - |
                 bash /root/.cache/tests/run.sh
-                tail -f /dev/null
             resources:
               limits:
                 huawei.com/ascend-1980: "16"