Checklist

• 1. I have searched related issues but cannot get the expected help.
• 2. The bug has not been fixed in the latest version.
• 3. Please note that if the bug-related issue you submitted lacks corresponding environment info and a minimal reproducible demo, it will be challenging for us to reproduce and resolve the issue, reducing the likelihood of receiving feedback.
• 4. If the issue you raised is not a bug but a question, please raise a discussion at https://github.com/sgl-project/sglang/discussions/new/choose Otherwise, it will be closed.
• 5. Please use English, otherwise it will be closed.

Describe the bug

When use instance workload, after setting RecreateInstanceOnPodRestart to the instance, controller would not recreate the failed instance once one pod is failed or deleted.

The reason why is the RestartPolicy not cited in instance controller, therefore, the instance controller can not recognize this policy.

https://github.com/sgl-project/rbg/blob/main/api/workloads/v1alpha1/instance_types.go#L39

Reproduction

Construct a rbg with instance workload, and set the size of the instance to more than one. And try to delete one pod, the other pods in the same instance will not restart nor be recreated, which is unexpected.

Environment

latest version, v0.6.0