Release Notes
TOC
Alauda AI Platform 2.9.0 (Fast)Upgrade SupportChanges from Alauda AI Platform 2.8MaaS usage changesKnown IssuesAlauda AI Platform 2.9.0 (Fast)
Alauda AI Platform 2.9.0 is a Fast release. These notes summarize the major platform, model-serving, training, and MLOps changes introduced since Alauda AI Platform 2.8.
Upgrade Support
Alauda AI Platform 2.9.0 Fast does not support upgrades from previous releases, including 2.8. Deploy it as a new installation.
Changes from Alauda AI Platform 2.8
- Alauda Build of Llama Stack: Deprecated and not recommended for use.
AmlClusterno longer manages this component. Consider Ogx as an alternative; Llama Stack deployment and usage guides have been removed. - Platform Configuration: The Admin view adds a Platform Configuration page for editing most supported
AmlClustersettings through the UI, including component management states and component-specific configuration. Advanced or unsupported fields remain available through the YAML view. - Inference service management: LLM inference services and regular inference services are listed and managed separately, making their different configuration and lifecycle options explicit.
- LLM inference configuration: LLM inference services support prefill/decode (P/D) disaggregation and configurable parallelism parameters, including tensor, pipeline, data, and expert parallelism when supported by the selected runtime.
- Alauda Build of InferNex Bridge: Added
infernexBridgecomponent management through thedefaultAmlCluster. - Alauda AI Platform NPU Serving Runtime: New component at version
v1.0.0, managed throughservingRuntimeNPUOperatorin thedefaultAmlCluster, with the vLLM-Ascendv0.23.0image included. - Alauda AI Platform Gateway: Updated to product version
v1.1.0-1. Its upstream project is now Agent Router, formerly Envoy AI Gateway. - Alauda AI Platform Inference Management: Updated to product version
v0.20.0-1, based on KServe. - Alauda AI Platform Serving Runtime: The Serving Runtime is upgraded to version
v1.2.2, and its vLLM image is upgraded tov0.23.0. The separate llm-d image is no longer used; llm-d reuses the vLLM image.
MaaS usage changes
- Published models use
MaaSModelRefv1alpha2: one published client model can now have multiple upstreams. An upstream can be anInferenceService,LLMInferenceService, or externalAIServiceBackend. - Model publishing is centralized: administrators create and edit models from MaaS → Models → Published Models. Importing an external model service only creates the external backend; it no longer directly publishes separate MaaS models from the service page.
- Inference services are upstream candidates: model owners mark an
InferenceServiceorLLMInferenceServicewithmaas.alauda.io/available: "true"before it can be selected as an upstream. - Client and provider model names are separate:
clientModelNameis the name applications send in the requestmodelfield and the name used by subscriptions, authorization, quotas, and usage reporting. An upstream can specify a differentupstreamModelNamefor the provider. - Multi-upstream routing: published models support upstream priority and weight configuration, allowing primary/backup and same-priority traffic distribution scenarios, plus request-level retry and failover settings.
- Subscriptions identify models by client model name: the same client model name cannot be added more than once to a subscription, even when it is backed by different
MaaSModelRefresources. - Usage reports distinguish model names: administrator reports and CSV exports can distinguish the client model from the upstream model.
Known Issues
- When VictoriaMetrics is used to collect monitoring data for inference services running in Serverless mode, inference services may not scale down to zero.