#Release Notes

#AI 2.6.0

#New and Optimized Features

#Single-Cluster Application Architecture

Alauda AI is changed to a single-cluster application deployment model. The former aml-global component is no longer delivered, and the Alauda AI product entry is configured from Administrator > Platform Settings > Platform Parameters > Integrated Product Configuration.

This release is a Fast release and supports only fresh installation. Upgrade from earlier Alauda AI versions is not supported in this release.

#Header and Navigation Simplification

Header and navigation are simplified for the new single-cluster experience. The logo and product name are provided by the platform solution configuration. Project and cluster switching are removed, and users switch only the active namespace in the Alauda AI console.

Maintenance status, license status, and the help entry are no longer displayed in the header. Language package configuration is moved to backend solution configuration.

#Authentication Integration

Authentication is integrated with oauth2-proxy for login and logout flows. Alauda AI also supports configuring an independent OIDC provider and an independent access entry.

#Namespace Management

Namespace management is enhanced in the administration view. Administrators can create namespaces from Alauda AI, import existing namespaces, and add members to a namespace as owners, editors, or viewers.

Namespace owners can manage namespace settings from User View, except for resource quota settings.

#Namespace Permission Model

Namespace-scoped user permissions replace the former platform roles aml-namespace-editor, owner, and viewer. Configure namespace members and their owner, editor, or viewer permissions from namespace member management instead of relying on the old platform roles.

#Monitoring

Monitoring data on the overview page is provided by backend integration with Prometheus. Alauda AI also introduces Perses-based monitoring dashboards.

#NPU Operator Integration

Alauda Build of NPU Operator is upgraded to v1.2.4 and can be deployed and managed by the AML Operator. This release adds adaptation for Ascend 910B and immutable OS environments.

#Deprecated Features

The former platform roles aml-namespace-editor, owner, and viewer are deprecated and are no longer used by the Alauda AI permission model.

#Breaking Changes

#Fresh Installation Only

AI 2.6.0 does not support upgrade from AI 2.5.x or earlier versions. Existing environment migration is outside the scope of this Fast release and requires a later LTS release with a dedicated upgrade guide.

#Product Entry Configuration

aml-global is removed. Register the Alauda AI product entry through Administrator > Platform Settings > Platform Parameters > Integrated Product Configuration.

#Navigation Changes

Project and cluster switching are removed from the header. Use namespace switching to change the working context.

#Permission Model Changes

The old platform roles aml-namespace-editor, owner, and viewer no longer apply. Configure user permissions from namespace user permission management.

#Logout Flow Changes

Login and logout are handled through oauth2-proxy. The login page appearance may differ from earlier versions.

#Fixed Issues

None. AI 2.6.0 is a Fast feature release and does not include fixes for defects inherited from earlier versions.

#Known Issues

• AI-24758: In Ascend 310P and vllm-ascend scenarios, inference services cannot run properly.
• AI-24759: In Knative Serving scenarios, queue-proxy may fail to start because runAsNonRoot does not match the image user.
• AI-24753: In some managed cluster environments, the HAMi scheduler image may fail to pull.
• AI-24754: The Workbench list may show duplicate WorkspaceKind entries.
• AI-24757: Model Catalog UI user identity parsing is inconsistent with other interfaces.
• AI-24755: Some frontend interactions and display behavior need optimization across Playground, inference services, Catalog, Model Registry, Workspace, and ServingRuntime pages.
• IDP-1533: After copying the KnativeServing example from the online documentation, the copied content may fail to create a resource correctly.
• AI-24760: The default resource request for model-catalog-ui is high: CPU 500m and memory 2Gi.
• AI-24733: The device management page does not include a documentation link for NPU Operator.

#Compatibility

AI 2.6.0 supports ACP 4.0, 4.1, 4.2, and 4.3. Kubernetes support follows the supported ACP versions, and release testing covered Kubernetes 1.32.11 to 1.34.5.

AI 2.6.0 supports multi-arch deployment on x86 and Arm. Release testing covered MicroOS, KubeOS, KylinOS V10, Ubuntu 22.04, RHEL 9.6, and other operating systems listed in the release test plan.

AI 2.6.0 supports IPv4 single stack, IPv6 single stack, and IPv4/IPv6 dual stack networks. Accelerator support includes NVIDIA GPU with HAMi or Device Plugin, and Ascend chips with NPU Operator.