[CI] Optimize nightly CI (#3898)

### What this PR does / why we need it?
This patch mainly fix the the problem of not being able to determine the
exit status of the pod's entrypoint script and some other tiny
optimizations:
1. Shorten wait for server timeout
2. fix typo
3. fix the issue of ais_bench failing to correctly access the proxy URL
in a PD separation scenario.
### Does this PR introduce _any_ user-facing change?

### How was this patch tested?


- vLLM version: v0.11.0
- vLLM main:
83f478bb19

---------

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

tests/e2e/nightly/multi_node/config/models/DeepSeek-R1-W8A8-A2-torchair.yaml

@@ -0,0 +1,64 @@
+test_name: "test DeepSeek-R1-W8A8 torchair on A2"
+model: "vllm-ascend/DeepSeek-R1-0528-W8A8"
+num_nodes: 2
+npu_per_node: 8
+env_common:
+  VLLM_USE_MODELSCOPE: true
+  HCCL_BUFFSIZE: 1024
+  SERVER_PORT: 8080
+  OMP_PROC_BIND: false
+  OMP_NUM_THREADS: 10
+
+
+deployment:
+  -
+    server_cmd: >
+      vllm serve vllm-ascend/DeepSeek-R1-0528-W8A8
+      --host 0.0.0.0
+      --port $SERVER_PORT
+      --data-parallel-size 4
+      --data-parallel-size-local 2
+      --data-parallel-address $LOCAL_IP
+      --data-parallel-rpc-port 13399
+      --no-enable-prefix-caching
+      --max-num-seqs 16
+      --tensor-parallel-size 4
+      --max-model-len 36864
+      --max-num-batched-tokens 6000
+      --enable-expert-parallel
+      --trust-remote-code
+      --quantization ascend
+      --gpu-memory-utilization 0.9
+      --speculative-config '{"num_speculative_tokens": 1, "method":"deepseek_mtp"}'
+      --additional-config '{"ascend_scheduler_config":{"enabled":false},"torchair_graph_config":{"enabled":true,"enable_multistream_moe":true},"chunked_prefill_for_mla":true,"enable_weight_nz_layout":true}'
+
+  -
+    server_cmd: >
+      vllm serve vllm-ascend/DeepSeek-R1-0528-W8A8
+      --headless
+      --data-parallel-size 4
+      --data-parallel-rpc-port 13399
+      --data-parallel-size-local 2
+      --data-parallel-start-rank 2
+      --data-parallel-address $MASTER_IP
+      --no-enable-prefix-caching
+      --max-num-seqs 16
+      --tensor-parallel-size 4
+      --max-model-len 36864
+      --max-num-batched-tokens 6000
+      --enable-expert-parallel
+      --trust-remote-code
+      --quantization ascend
+      --gpu-memory-utilization 0.9
+      --speculative-config '{"num_speculative_tokens": 1, "method":"deepseek_mtp"}'
+      --additional-config '{"ascend_scheduler_config":{"enabled":false},"torchair_graph_config":{"enabled":true,"enable_multistream_moe":true},"chunked_prefill_for_mla":true,"enable_weight_nz_layout":true}'
+benchmarks:
+  acc:
+    case_type: accuracy
+    dataset_path: vllm-ascend/gsm8k
+    request_conf: vllm_api_general_chat
+    dataset_conf: gsm8k/gsm8k_gen_0_shot_cot_chat_prompt
+    max_out_len: 32768
+    batch_size: 512
+    baseline: 95
+    threshold: 5