diff --git a/infra/k8s/argo/compile-and-train-template.yaml b/infra/k8s/argo/compile-and-train-template.yaml index 0ebd49b7b..c17973c2d 100644 --- a/infra/k8s/argo/compile-and-train-template.yaml +++ b/infra/k8s/argo/compile-and-train-template.yaml @@ -17,6 +17,7 @@ metadata: labels: app.kubernetes.io/name: compile-and-train app.kubernetes.io/part-of: foxhunt + app.kubernetes.io/component: gpu-test spec: entrypoint: pipeline onExit: notify-result @@ -24,6 +25,7 @@ spec: podMetadata: labels: app.kubernetes.io/part-of: foxhunt + app.kubernetes.io/component: gpu-test app.kubernetes.io/component: compile-and-train # No runAsUser — compile (ci-builder) needs root, training runtime defaults # to its image user. fsGroup ensures workspace PVC is writable by all pods. diff --git a/infra/k8s/argo/train-dqn-template.yaml b/infra/k8s/argo/train-dqn-template.yaml index 1489a4f85..7444439e1 100644 --- a/infra/k8s/argo/train-dqn-template.yaml +++ b/infra/k8s/argo/train-dqn-template.yaml @@ -15,12 +15,14 @@ metadata: labels: app.kubernetes.io/name: train-dqn app.kubernetes.io/part-of: foxhunt + app.kubernetes.io/component: gpu-test spec: entrypoint: pipeline serviceAccountName: argo-workflow podMetadata: labels: app.kubernetes.io/part-of: foxhunt + app.kubernetes.io/component: gpu-test app.kubernetes.io/component: training securityContext: runAsUser: 1000 diff --git a/infra/k8s/argo/train-ppo-template.yaml b/infra/k8s/argo/train-ppo-template.yaml index c316f8199..35bd495e1 100644 --- a/infra/k8s/argo/train-ppo-template.yaml +++ b/infra/k8s/argo/train-ppo-template.yaml @@ -15,12 +15,14 @@ metadata: labels: app.kubernetes.io/name: train-ppo app.kubernetes.io/part-of: foxhunt + app.kubernetes.io/component: gpu-test spec: entrypoint: pipeline serviceAccountName: argo-workflow podMetadata: labels: app.kubernetes.io/part-of: foxhunt + app.kubernetes.io/component: gpu-test app.kubernetes.io/component: training securityContext: runAsUser: 1000 diff --git a/infra/k8s/argo/train-supervised-template.yaml b/infra/k8s/argo/train-supervised-template.yaml index bce1e825e..75c88c54b 100644 --- a/infra/k8s/argo/train-supervised-template.yaml +++ b/infra/k8s/argo/train-supervised-template.yaml @@ -18,12 +18,14 @@ metadata: labels: app.kubernetes.io/name: train-supervised app.kubernetes.io/part-of: foxhunt + app.kubernetes.io/component: gpu-test spec: entrypoint: pipeline serviceAccountName: argo-workflow podMetadata: labels: app.kubernetes.io/part-of: foxhunt + app.kubernetes.io/component: gpu-test app.kubernetes.io/component: training securityContext: runAsUser: 1000 diff --git a/infra/k8s/argo/training-workflow-template.yaml b/infra/k8s/argo/training-workflow-template.yaml index c7bba703f..1fa263bcd 100644 --- a/infra/k8s/argo/training-workflow-template.yaml +++ b/infra/k8s/argo/training-workflow-template.yaml @@ -6,6 +6,7 @@ metadata: labels: app.kubernetes.io/name: training-pipeline app.kubernetes.io/part-of: foxhunt + app.kubernetes.io/component: gpu-test spec: entrypoint: train-model serviceAccountName: argo-workflow @@ -13,6 +14,7 @@ spec: podMetadata: labels: app.kubernetes.io/part-of: foxhunt + app.kubernetes.io/component: gpu-test app.kubernetes.io/component: training-workflow securityContext: runAsUser: 1000