[v0.18.0][Test][Misc] Update CI for GLM-5 configuration on vllm-ascend/releases/v0.18.0 branch (#8322)

<!--  Thanks for sending a pull request!

BEFORE SUBMITTING, PLEASE READ
https://docs.vllm.ai/en/latest/contributing/overview.html

-->
### What this PR does / why we need it?
Update CI for GLM-5 configuration on vllm-ascend/releases/v0.18.0 branch
在0.18.0版本上对glm5-w4a8做测试

### Does this PR introduce _any_ user-facing change?
<!--
Note that it means *any* user-facing change including all aspects such
as API, interface or other behavior changes.
Documentation-only updates are not considered user-facing changes.
-->

### How was this patch tested?
<!--
CI passed with new added/existing test.
If it was tested in a way different from regular unit tests, please
clarify how you tested step by step, ideally copy and paste-able, so
that other reviewers can test and check, and descendants can verify in
the future.
If tests were not added, please describe why they were not added and/or
why it was difficult to add.
-->

---------

Signed-off-by: yangjiuhua <y00845194@china.huawei.com>
Co-authored-by: yangjiuhua <y00845194@china.huawei.com>

tests/e2e/nightly/single_node/models/configs/GLM-5.yaml

@@ -9,7 +9,6 @@ _envs: &envs
   OMP_PROC_BIND: "false"
   OMP_NUM_THREADS: "1"
   PYTORCH_NPU_ALLOC_CONF: "expandable_segments:True"
-
 _server_cmd: &server_cmd
   - "--enable-expert-parallel"
   - "--tensor-parallel-size"
@@ -19,7 +18,7 @@ _server_cmd: &server_cmd
   - "--port"
   - "$SERVER_PORT"
   - "--max-model-len"
-  - "8192"
+  - "16384"
   - "--max-num-batched-tokens"
   - "4096"
   - "--trust-remote-code"
@@ -31,7 +30,7 @@ _server_cmd: &server_cmd
   - "ascend"
   - "--async-scheduling"
   - "--additional-config"
-  - '{"enable_npugraph_ex": true,"fuse_muls_add":true,"multistream_overlap_shared_expert":true}'
+  - '{"fuse_muls_add": true, "multistream_overlap_shared_expert": false, "ascend_compilation_config": {"enable_npugraph_ex": true}}'
   - "--speculative-config"
   - '{"num_speculative_tokens": 3, "method": "deepseek_mtp"}'
 
@@ -44,7 +43,7 @@ _benchmarks: &benchmarks
     dataset_path: vllm-ascend/gsm8k-lite
     request_conf: vllm_api_general_chat
     dataset_conf: gsm8k/gsm8k_gen_0_shot_cot_chat_prompt
-    max_out_len: 4096
+    max_out_len: 8192
     batch_size: 8
     baseline: 95
     threshold: 5