[CI] Refator multi-node CI (#3487)

### What this PR does / why we need it?
Refactor the multi-machine CI use case. The purpose of this PR is to
increase the ease of adding multi-machine CI use cases, allowing
developers to add multi-machine cluster model testing use cases
(including PD separation) by simply adding a new YAML configuration
file.
### Does this PR introduce _any_ user-facing change?

### How was this patch tested?

- vLLM version: v0.11.0rc3
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.0

---------

Signed-off-by: wangli <wangli858794774@gmail.com>
This commit is contained in:
Li Wang
2025-10-17 09:04:31 +08:00
committed by GitHub
parent ccb6fb9ec1
commit 4c4a8458a5
18 changed files with 632 additions and 437 deletions

View File

@@ -102,6 +102,15 @@ jobs:
wait $LOG_PID || true
kill $MONITOR_PID || true
- name: Generate summary
if: always()
run: |
if [ -f "/root/.cache/test_summary.md" ]; then
cat /root/.cache/test_summary.md >> "$GITHUB_STEP_SUMMARY"
else
echo "No summary file found." >> "$GITHUB_STEP_SUMMARY"
fi
- name: Post process
if: always()
run: |