infra: add suspended CronWorkflow for nightly GPU test runs
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
25
infra/k8s/argo/gpu-test-nightly-cron.yaml
Normal file
25
infra/k8s/argo/gpu-test-nightly-cron.yaml
Normal file
@@ -0,0 +1,25 @@
|
||||
# infra/k8s/argo/gpu-test-nightly-cron.yaml
|
||||
apiVersion: argoproj.io/v1alpha1
|
||||
kind: CronWorkflow
|
||||
metadata:
|
||||
name: gpu-test-nightly
|
||||
namespace: foxhunt
|
||||
labels:
|
||||
app.kubernetes.io/name: gpu-test-nightly
|
||||
app.kubernetes.io/part-of: foxhunt
|
||||
spec:
|
||||
schedule: "0 2 * * *"
|
||||
timezone: "UTC"
|
||||
suspend: true # Enable when ready: kubectl patch cronworkflow gpu-test-nightly -n foxhunt -p '{"spec":{"suspend":false}}'
|
||||
concurrencyPolicy: Replace
|
||||
successfulJobsHistoryLimit: 3
|
||||
failedJobsHistoryLimit: 5
|
||||
workflowSpec:
|
||||
workflowTemplateRef:
|
||||
name: gpu-test-pipeline
|
||||
arguments:
|
||||
parameters:
|
||||
- name: models
|
||||
value: "dqn,ppo,tft,mamba2,tggn,tlob,liquid,kan,xlstm,diffusion"
|
||||
- name: commit-ref
|
||||
value: "main"
|
||||
Reference in New Issue
Block a user