Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 4 additions & 5 deletions .github/workflows/katib_test.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -23,7 +23,10 @@ jobs:
runs-on: ubuntu-latest
steps:
- name: Checkout
uses: actions/checkout@v4
uses: actions/checkout@v5

- name: Free up disk space
run: ./tests/free-disk-space.sh

- name: Install KinD, Create KinD cluster and Install kustomize
run: ./tests/install_KinD_create_KinD_cluster_install_kustomize.sh
Expand Down Expand Up @@ -55,10 +58,6 @@ jobs:
- name: Install Katib
run: ./tests/katib_install.sh


- name: Install Dependencies
run: pip install pytest kubernetes kfp==2.13.0 requests

- name: Port-forward the istio-ingress gateway
run: ./tests/port_forward_gateway.sh

Expand Down
2 changes: 1 addition & 1 deletion README.md
Original file line number Diff line number Diff line change
Expand Up @@ -67,7 +67,7 @@ This repository periodically synchronizes all official Kubeflow components from
| Jupyter Web Application | applications/jupyter/jupyter-web-app/upstream | [v1.10.0](https://github.com/kubeflow/kubeflow/tree/v1.10.0/components/crud-web-apps/jupyter/manifests) | 4m | 231Mi | 0GB |
| Tensorboards Web Application | applications/tensorboard/tensorboards-web-app/upstream | [v1.10.0](https://github.com/kubeflow/kubeflow/tree/v1.10.0/components/crud-web-apps/tensorboards/manifests) | | | |
| Volumes Web Application | applications/volumes-web-app/upstream | [v1.10.0](https://github.com/kubeflow/kubeflow/tree/v1.10.0/components/crud-web-apps/volumes/manifests) | 4m | 226Mi | 0GB |
| Katib | applications/katib/upstream | [v0.18.0](https://github.com/kubeflow/katib/tree/v0.18.0/manifests/v1beta1) | 13m | 476Mi | 10GB |
| Katib | applications/katib/upstream | [v0.19.0](https://github.com/kubeflow/katib/tree/v0.19.0/manifests/v1beta1) | 13m | 476Mi | 10GB |
| KServe | applications/kserve/kserve | [v0.15.0](https://github.com/kserve/kserve/releases/tag/v0.15.0/install/v0.15.0) | 600m | 1200Mi | 0GB |
| KServe Models Web Application | applications/kserve/models-web-app | [v0.15.0](https://github.com/kserve/models-web-app/tree/v0.15.0/config) | 6m | 259Mi | 0GB |
| Kubeflow Pipelines | applications/pipeline/upstream | [2.15.0](https://github.com/kubeflow/pipelines/tree/2.15.0/manifests/kustomize) | 970m | 3552Mi | 35GB |
Expand Down
22 changes: 15 additions & 7 deletions applications/katib/upstream/components/controller/rbac.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -91,15 +91,23 @@ rules:
- "create"
- "delete"
- apiGroups:
- trainer.kubeflow.org
- jobset.x-k8s.io
resources:
- trainjobs
- jobsets
verbs:
- "get"
- "list"
- "watch"
- "create"
- "delete"
- "get"
- "list"
- "watch"
- apiGroups:
- trainer.kubeflow.org
resources:
- trainjobs
verbs:
- "create"
- "get"
- "list"
- "watch"
- "delete"
- apiGroups:
- kubeflow.org
resources:
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -15,7 +15,7 @@ data:
spec:
containers:
- name: training-container
image: ghcr.io/kubeflow/katib/pytorch-mnist-cpu:v0.18.0
image: ghcr.io/kubeflow/katib/pytorch-mnist-cpu:v0.19.0
command:
- "python3"
- "/opt/pytorch-mnist/mnist.py"
Expand All @@ -33,7 +33,7 @@ data:
spec:
containers:
- name: training-container
image: ghcr.io/kubeflow/katib/enas-cnn-cifar10-cpu:v0.18.0
image: ghcr.io/kubeflow/katib/enas-cnn-cifar10-cpu:v0.19.0
command:
- python3
- -u
Expand All @@ -54,7 +54,7 @@ data:
spec:
containers:
- name: pytorch
image: ghcr.io/kubeflow/katib/pytorch-mnist-cpu:v0.18.0
image: ghcr.io/kubeflow/katib/pytorch-mnist-cpu:v0.19.0
command:
- "python3"
- "/opt/pytorch-mnist/mnist.py"
Expand All @@ -68,7 +68,7 @@ data:
spec:
containers:
- name: pytorch
image: ghcr.io/kubeflow/katib/pytorch-mnist-cpu:v0.18.0
image: ghcr.io/kubeflow/katib/pytorch-mnist-cpu:v0.19.0
command:
- "python3"
- "/opt/pytorch-mnist/mnist.py"
Expand Down
5 changes: 2 additions & 3 deletions applications/katib/upstream/components/ui/ui.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -17,9 +17,6 @@ spec:
katib.kubeflow.org/component: ui
sidecar.istio.io/inject: "false"
spec:
securityContext:
seccompProfile:
type: RuntimeDefault
containers:
- name: katib-ui
image: ghcr.io/kubeflow/katib/katib-ui
Expand All @@ -39,6 +36,8 @@ spec:
runAsNonRoot: true
allowPrivilegeEscalation: false
runAsUser: 1000
seccompProfile:
type: RuntimeDefault
capabilities:
drop:
- ALL
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -5,10 +5,10 @@ metadata:
name: katib-webhook-cert
spec:
isCA: true
commonName: $(KATIB_SERVICE_NAME).$(KATIB_NAMESPACE).svc
commonName: KATIB_SERVICE_NAME_PLACEHOLDER.KATIB_NAMESPACE_PLACEHOLDER.svc
dnsNames:
- $(KATIB_SERVICE_NAME).$(KATIB_NAMESPACE).svc
- $(KATIB_SERVICE_NAME).$(KATIB_NAMESPACE).svc.cluster.local
- KATIB_SERVICE_NAME_PLACEHOLDER.KATIB_NAMESPACE_PLACEHOLDER.svc
- KATIB_SERVICE_NAME_PLACEHOLDER.KATIB_NAMESPACE_PLACEHOLDER.svc.cluster.local
issuerRef:
kind: Issuer
name: katib-selfsigned-issuer
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -5,6 +5,7 @@ init:
controller:
webhookPort: 8443
trialResources:
- TrainJob.v1alpha1.trainer.kubeflow.org
- Job.v1.batch
- TFJob.v1.kubeflow.org
- PyTorchJob.v1.kubeflow.org
Expand All @@ -13,40 +14,40 @@ init:
runtime:
metricsCollectors:
- kind: StdOut
image: ghcr.io/kubeflow/katib/file-metrics-collector:v0.18.0
image: ghcr.io/kubeflow/katib/file-metrics-collector:v0.19.0
- kind: File
image: ghcr.io/kubeflow/katib/file-metrics-collector:v0.18.0
image: ghcr.io/kubeflow/katib/file-metrics-collector:v0.19.0
- kind: TensorFlowEvent
image: ghcr.io/kubeflow/katib/tfevent-metrics-collector:v0.18.0
image: ghcr.io/kubeflow/katib/tfevent-metrics-collector:v0.19.0
resources:
limits:
memory: 1Gi
suggestions:
- algorithmName: random
image: ghcr.io/kubeflow/katib/suggestion-hyperopt:v0.18.0
image: ghcr.io/kubeflow/katib/suggestion-hyperopt:v0.19.0
- algorithmName: tpe
image: ghcr.io/kubeflow/katib/suggestion-hyperopt:v0.18.0
image: ghcr.io/kubeflow/katib/suggestion-hyperopt:v0.19.0
- algorithmName: grid
image: ghcr.io/kubeflow/katib/suggestion-optuna:v0.18.0
image: ghcr.io/kubeflow/katib/suggestion-optuna:v0.19.0
- algorithmName: hyperband
image: ghcr.io/kubeflow/katib/suggestion-hyperband:v0.18.0
image: ghcr.io/kubeflow/katib/suggestion-hyperband:v0.19.0
- algorithmName: bayesianoptimization
image: ghcr.io/kubeflow/katib/suggestion-skopt:v0.18.0
image: ghcr.io/kubeflow/katib/suggestion-skopt:v0.19.0
- algorithmName: cmaes
image: ghcr.io/kubeflow/katib/suggestion-goptuna:v0.18.0
image: ghcr.io/kubeflow/katib/suggestion-goptuna:v0.19.0
- algorithmName: sobol
image: ghcr.io/kubeflow/katib/suggestion-goptuna:v0.18.0
image: ghcr.io/kubeflow/katib/suggestion-goptuna:v0.19.0
- algorithmName: multivariate-tpe
image: ghcr.io/kubeflow/katib/suggestion-optuna:v0.18.0
image: ghcr.io/kubeflow/katib/suggestion-optuna:v0.19.0
- algorithmName: enas
image: ghcr.io/kubeflow/katib/suggestion-enas:v0.18.0
image: ghcr.io/kubeflow/katib/suggestion-enas:v0.19.0
resources:
limits:
memory: 400Mi
- algorithmName: darts
image: ghcr.io/kubeflow/katib/suggestion-darts:v0.18.0
image: ghcr.io/kubeflow/katib/suggestion-darts:v0.19.0
- algorithmName: pbt
image: ghcr.io/kubeflow/katib/suggestion-pbt:v0.18.0
image: ghcr.io/kubeflow/katib/suggestion-pbt:v0.19.0
persistentVolumeClaimSpec:
accessModes:
- ReadWriteMany
Expand All @@ -55,4 +56,4 @@ runtime:
storage: 5Gi
earlyStoppings:
- algorithmName: medianstop
image: ghcr.io/kubeflow/katib/earlystopping-medianstop:v0.18.0
image: ghcr.io/kubeflow/katib/earlystopping-medianstop:v0.19.0
Loading
Loading