[CI] Optimize nightly CI (#3858)

### What this PR does / why we need it?
This patch optimize nightly CI:
1. Bug fixes ais_bench get None repo_type error
2. Fix A2 install kubectl error with arm arch
3. Fix the multi_node CI unable to determine whether the job was
successful error
### Does this PR introduce _any_ user-facing change?

### How was this patch tested?


- vLLM version: v0.11.0rc3
- vLLM main:
83f478bb19

---------

Signed-off-by: wangli <wangli858794774@gmail.com>
This commit is contained in:
Li Wang
2025-10-29 22:30:19 +08:00
committed by GitHub
parent cba69e117e
commit 4a2ab13743
8 changed files with 110 additions and 39 deletions

View File

@@ -65,6 +65,7 @@ concurrency:
jobs:
e2e:
name: ${{ inputs.config_file_path }}
# This is a runner with no NPU for k8s controller
runs-on: ${{ inputs.runner }}
container:
@@ -112,9 +113,10 @@ jobs:
# prepare for lws entrypoint scripts
install -D tests/e2e/nightly/multi_node/scripts/run.sh /root/.cache/tests/run.sh
- name: Clear result ret
- name: Clear resources
run: |
rm -f $RESULT_FILE
# pre clear the crd resources created by lws
kubectl delete leaderworkerset vllm -n "$NAMESPACE" --ignore-not-found
- name: Launch cluster
run: |
@@ -153,6 +155,8 @@ jobs:
-D vllm_ascend_ref="$vllm_ascend_ref" \
-D result_file_path="$result_file_path" \
-D npu_per_node="$npu_per_node" \
-D controller_name="$HOSTNAME" \
-D kb_secret=${{ secrets.KUBECONFIG_B64 }} \
--outfile lws.yaml
kubectl apply -f ./lws.yaml
@@ -178,29 +182,6 @@ jobs:
run: |
kubectl logs -f "$LEADER_POD" -n "$NAMESPACE"
- name: Determine is success
run: |
TIMEOUT=300
ELAPSED=0
while [ ! -f "$RESULT_FILE" ]; do
sleep 5
ELAPSED=$((ELAPSED + 5))
if [ $ELAPSED -ge $TIMEOUT ]; then
echo "Timeout waiting for test result file"
exit 1
fi
done
RET=$(cat "$RESULT_FILE")
echo "Test result: $RET"
if [ "$RET" -ne 0 ]; then
echo "Test failed"
exit 1
else
echo "Test succeeded"
fi
- name: Post process
if: always()
run: |