Key concepts

Kubeflow on KakaoCloud is an open-source platform that helps easily build and run machine learning workflows in a cloud-native environment. Built on Kubernetes, it leverages Kubernetes' cluster management capabilities to simplify and streamline the management of ML workflows.

It provides key components for ML workflows such as data preprocessing, model training, and model serving, allowing developers to quickly and easily build ML models using a consistent interface and high-level abstractions.

Resource structure

Resource structure

Item	Description
⓵ Cloud	Runs in the KakaoCloud environment Utilizes cloud infrastructure to simplify ML tasks
⓶ Kubernetes engine and cluster	Kubeflow is based on Kubernetes engine and cluster Enables easier ML model development, deployment, and management
⓷ Kubeflow application	Provides essential functionality for developing, tuning, deploying, and managing ML models
⓸ Kubeflow scaffolding	Provides functions necessary for ML model deployment and management
⓹ Machine learning tools	Supports various ML tools Users can choose preferred tools for ML tasks

ML workflow

Phase	Step	Description
Experiment phase	Data collection and preprocessing	Collect and preprocess data for ML model training
	Data transformation	Transform data into a format that models can understand, reduce size, extract features
	Model coding	Write code to develop models based on selected algorithms
	Model training	Train models on data, try different hyperparameters and compare models
	Hyperparameter tuning	Adjust hyperparameters to find optimal model
Production phase	Model training and evaluation	Train the final model and evaluate performance
	Model deployment	Deploy trained models to provide prediction services
	Monitoring and management	Monitor performance and stability of models, respond to issues

Kubeflow lifecycle and status

Kubeflow lifecycle

Status	Description	Label
Creating	Kubeflow resources are being created	Yellow
Active	Kubeflow resources have been successfully created and are active	Green
Failed	Creation failed or unexpected error occurred	Red
Expired	Resources expired or associated cluster deleted	Red
Terminating	Resources are being terminated	Yellow
Terminated	Resources have been terminated	Gray

info

For information about the status of clusters, node pools, and nodes used with Kubeflow, refer to Kubernetes Engine > Resource status information.

Kubeflow user and group status

Kubeflow user and group status

Status	Description	Label
Pending	User or group is being created/modified	Yellow
Active	Creation/modification completed successfully	Green
Failed	Failed due to error during user/group operations	Red
Deleted	Deletion completed successfully	Not displayed

Kubeflow component architecture

Components in Kubeflow are small modular units that manage the ML workflow. They offer flexibility, scalability, and automation for tasks such as model development and deployment.

Component type	Description
Dashboard	Web console for accessing Kubeflow components
JupyterLab	Web-based ML development tool integrated with Kubeflow SDK
Kubeflow Pipelines	Visual console for managing ML workflows like preprocessing, training, serving
Katib	Hyperparameter optimization tool for model training in distributed environments
KServe	Serves models trained in Kubeflow via REST API
Training Operator	Supports distributed training for frameworks like TensorFlow, PyTorch
Model Registry	Stores metadata for model registration and versioning, integrates with other components

Supported components by version and service type

Version	Service type	Components and versions
1.6.0	Essential + Hyper Param Tuning (HPT) + Serving API	- JupyterLab 3.2.9 - KF Pipelines 2.0.0-alpha.5 - Katib 0.15.0 - Tensorboard 2.1.0 - KServe 0.8.0
1.8.0	Essential + Hyper Param Tuning (HPT) + Serving API	- JupyterLab 4.2.1 - KF Pipelines 2.0.5 - Katib 0.16.0 - Tensorboard 2.5.1 - KServe 0.11.2

Manage Kubeflow roles

Kubeflow roles define the level of access and control over the console, dashboard, and namespaces.
Roles include Owner, User, and Group User. A single user may have multiple roles.

Role types at the Kubeflow level

info

To become a Kubeflow Owner, IAM Project Member permissions are required.
Removing IAM permissions after becoming an Owner may prevent console and dashboard access.

Role	Description
Kubeflow owner	Automatically assigned to the user who creates the Kubeflow instance - Can manage users, namespaces, and groups - At least one owner is required per instance (max 5 allowed) - Requires IAM project manager/member privileges
Kubeflow user	Regular user who can manage their namespace or participate in groups via the dashboard - Must be registered by a Kubeflow Owner or IAM admin - Cannot access the console without IAM permissions
Kubeflow group user	User registered to a group, able to access the dashboard based on group permissions - Can be registered via console or dashboard by an Admin - Can belong to multiple groups with separate roles per group - Roles: Admin / Edit / View

Console permissions by role

info

Roles other than Owner do not have console access. IAM project permissions are required. See IAM for more details.

Console permissions	Kubeflow owner
View Kubeflow details	✓
Request deletion	✓
Manage owners	✓
Manage users	✓
Manage groups	✓
Manage group users	✓

Dashboard permissions by role

info

A user’s role is valid only within their assigned namespace.
Users may have multiple roles across different namespaces. See below for permissions by role.

Dashboard permission	Owner	User	Group Admin	Group Edit	Group View
View other namespaces	✓
View own namespace	✓	✓	✓	✓	✓
Manage group users			✓
View notebooks	✓	✓	✓	✓	✓
Create/delete/edit notebooks	✓	✓	✓	✓
View Tensorboards	✓	✓	✓	✓	✓
Create/delete/edit Tensorboards	✓	✓	✓	✓
View pipelines	✓	✓	✓	✓	✓
Create/delete/edit pipelines	✓	✓	✓	✓
View AutoML (Katib)	✓	✓	✓	✓	✓
Create/delete/edit AutoML	✓	✓	✓	✓
View model serving (KServe)	✓	✓	✓	✓	✓
Create/delete/edit model serving	✓	✓	✓	✓