[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>
This commit is contained in:
Li Wang
2025-10-30 23:42:20 +08:00
committed by GitHub
parent 2c291bc63f
commit eb0a2ee2d0
14 changed files with 94 additions and 66 deletions

View File

@@ -18,7 +18,7 @@ spec:
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") }}
value: {{ config_file_path | default("DeepSeek-V3.yaml") }}
- name: WORKSPACE
value: "/root/workspace"
# Set vLLM version and vLLM-Ascend version here, once there is a new release, update here.
@@ -29,11 +29,9 @@ spec:
- 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") }}
- name: CONTROLLER_NAME
value: {{ controller_name | default("placeholder") }}
- name: SECRET
value: {{ kb_secret | default("placeholder") }}
value: {{ result_file_path | default("/root/.cache/tests/ret") }}
- name: FAIL_TAG
value: {{ fail_tag | default("FAIL_TAG") }}
command:
- sh
- -c
@@ -80,7 +78,7 @@ spec:
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") }}
value: {{ config_file_path | default("DeepSeek-V3.yaml") }}
- name: WORKSPACE
value: "/root/workspace"
# Set vLLM version and vLLM-Ascend version here, once there is a new release, update here.
@@ -92,6 +90,8 @@ spec:
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") }}
- name: FAIL_TAG
value: {{ fail_tag | default("FAIL_TAG") }}
command:
- sh
- -c