[2/N] Upgrade nightly doc (#5534)

### What this PR does / why we need it?
Follow up https://github.com/vllm-project/vllm-ascend/pull/5479, upgrade
the corresponding doc for developers

- vLLM version: v0.13.0
- vLLM main:
45c1ca1ca1

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

tests/e2e/nightly/multi_node/config/DeepSeek-V3.yaml

@@ -22,7 +22,7 @@ env_common:
   NUMEXPR_MAX_THREADS: 128
   DISAGGREGATED_PREFILL_PROXY_SCRIPT: "examples/disaggregated_prefill_v1/load_balance_proxy_server_example.py"
 # For None kubernetes deployment, list the IPs of all nodes used in order as follow
-# cluster_hosts: []
+# cluster_hosts: [10.0.0.103, 10.0.0.139]
 disaggregated_prefill:
   enabled: true
   prefiller_host_index: [0]

tests/e2e/nightly/multi_node/scripts/multi_node_config.py

@@ -340,6 +340,9 @@ class MultiNodeConfigLoader:
     @staticmethod
     def _resolve_cluster_ips(cfg: dict, num_nodes: int) -> list[str]:
         if "cluster_hosts" in cfg and cfg["cluster_hosts"]:
+            logger.info(
+                "Using cluster_hosts from config. This typically indicates that your current environment is a non-Kubernetes environment."
+            )
             ips = cfg["cluster_hosts"]
             if len(ips) != num_nodes:
                 raise AssertionError("cluster_hosts size mismatch")

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

@@ -26,7 +26,7 @@ print_section() {
 }
 
 print_failure() {
-    echo -e "${RED}${FAIL_TAG} ✗ ERROR: $1${NC}"
+    echo -e "${RED}${FAIL_TAG:-test_failed} ✗ ERROR: $1${NC}"
     exit 1
 }