sirius/gcloud-lab
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

fix: match vllm-l4 deployment nodeSelector and tolerations to nodepool labels/taints

Browse source
This commit is contained in:
Sirius Claw 2026-04-20 05:11:55 +00:00
parent 0ab2305c1c
commit 7d34b3f649
1 changed files with 3 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

5
apps/base/customer1/openclaw/vllm-l4.yaml
View file

@ -16,10 +16,11 @@ spec:
app: openclaw-brain-l4 app: openclaw-brain-l4
spec: spec:
nodeSelector: nodeSelector:
cloud.google.com/gke-accelerator: "nvidia-l4" workload: "llm-analyst"
tolerations: tolerations:
- key: "nvidia.com/gpu" - key: "nvidia.com/gpu"
operator: "Exists" operator: "Equal"
value: "present"
effect: "NoSchedule" effect: "NoSchedule"
containers: containers:
- name: vllm-brain-l4 - name: vllm-brain-l4