Files
file/ml-backend-1.0.4.tgz
Duc Nguyen 8a1cac6320 add ml-backend-1.0.4.tgz
Sizes resources to the tenant ResourceQuota (500m/4Gi limits, 500m/2Gi requests)
and switches to strategy: Recreate, so the pod no longer depends on the KubePlus
webhook to be admissible and a rollout can actually complete under the quota.

Chart source: py-ailbl-project-integration-pipeline @ 8145494
2026-08-17 16:10:02 +07:00

6.9 KiB