What's New

Major features and updates for the Cloudera AI data service.

March 18, 2026

Release notes and fixed issues for version 2.0.55-b196.

Cloudera AI Control Plane

Fixed a container runtime regression (runc v1.4.0) that caused health probe failures on Azure. The Buildkit DaemonSet probe mechanism was updated to ensure stable image builds and to guarantee that the MLX secret is preserved in the monitoring namespace during workspace upgrades and restorations. (DSE-52078)

Release notes and fixed issues for version 2.0.55-b193.

Cloudera AI Workbench

Improved application responsiveness by optimizing database query performance across projects and jobs, significantly reducing page load times for environments with large datasets.

Cloudera AI Control Plane

Improved consistency across the administrative experience for AI Workbench, AI Registry, and the AI Inference services.
Added support for Amazon EKS 1.33.
Added support for Azure AKS 1.33.
Improved the reliability of Cloudera AI Inference service upgrade processes.
Cloudera AI now automatically performs side-by-side upgrades for incompatible environments, ensuring a seamless one-click experience with built-in rollback support in case of failure. To upgrade a workbench, Cloudera users must hold both the MLAdmin and EnvironmentAdmin roles, and those performing an upgrade must also possess the necessary cloud provider permissions to execute backup and restore operations for the underlying storage and metadata databases. For more information, see Upgrading Cloudera AI Workbenches.

Cloudera AI Inference service

Cloudera AI Inference service now provides a production-grade serving environment for hosting applications. Applications deployed on Cloudera AI Inference service can scale alongside Model Endpoints, providing a scalable solution for various components. For more information, see Serving Applications on Cloudera AI Inference service (Technical Preview) .
Cloudera AI Inference service now supports AWS on-demand capacity reservations and capacity blocks to ensure compute availability for inference workloads. For more information, see Configuring AWS on-demand capacity reservations and capacity blocks.
Cloudera AI now supports the deployment of Hugging Face reranking models using the API.
Cloudera AI now supports deploying Hugging Face embedding models using the API.
You can now manually specify model tasks (such as EMBED, RANK, or CLASSIFICATION) using API during deployment, enabling broader vLLM support for architectures like bertmodel or modernbertfortokenclassification that serve tasks like embedding and reranking respectively.
You can now manage Cloudera AI Inference service logging globally using the Serving API ConfigMap, allowing administrators to enable logging and define a storage bucket across all endpoints simultaneously for consistent data collection.
Added Fine Grained Authorization support. For more information, see Configuring Fine-grained Access Control.

Cloudera AI Registry

Cloudera AI Inference service now supports direct deployment for XGBoost, PyTorch, and TensorFlow models using the AI Registry. For more information, see Deploying Additional Model Frameworks.
Cloudera AI Registry now displays structured metadata and comprehensive lineage tracking (provider, model ID, and SHA) for all models imported from Hugging Face and NVIDIA NGC.

Cloudera AI Workbench

Resolved an issue that prevented Team Administrators from updating the team description in the UI. (DSE-48770)
Fixed the workload status synchronisation issue between dashboards and dashboard_pods, ensuring accurate and consistent resource usage reporting. (DSE-46977)

Cloudera AI Inference service

Resolved an issue where Hugging Face model IDs in inference URLs were un-sanitized, causing routing failures; inference endpoints now correctly use underscores (_) instead of slashes to align with Triton directory structures and authorizer patterns. (DSE-50543)
Fixed an issue where Hugging Face embedding models failed to deploy to vLLM due to an unsupported embed task key. (DSE-49993)

Release notes and fixed issues for version 2.0.53-b273.

Cloudera AI Workbench

Added a new and dedicated Cloudera AI Overview page in the Control Plane. This page now serves as the primary landing page, replacing the previous Workspace Administration panel view. (DSE-43180)
Model endpoints now support the configuration of vetted environment variables using the UI and API. This enables specialized use cases, such as toggling reasoning output for NVIDIA NIMs. (DSE-45592)

Cloudera AI Platform

Added support for the AWS Bahrain region. (DSE-46039)
Added support for the Azure Spain region. (DSE-44839)
Added monitoring for metadata reporting, including the tracking of the workspace version (appVersion). (DSE-32676)

Cloudera AI Inference service

Cloudera AI Registry

Upgraded NIM-CLI to the latest version to incorporate improvements in memory management and error handling when downloading large models. (DSE-46374)
All critical and high-severity CVEs in Cloudera AI Registry have been addressed.
The Registered Models UI now loads successfully when using Google Chrome version 142 or above. (DSE-48824)

Cloudera AI Inference service

The Model Endpoints UI now loads successfully when using Google Chrome version 142 or above. (DSE-48824)

Cloudera AI Workbench

Resolved a critical race condition in the reconciler that caused successfully completed jobs to be incorrectly marked as failed with a -1 exit code. (DSE-48076 and DSE-44901)
The Spark UI button is now correctly displayed in the dropdown menu for Jupyter Notebooks within the Cloudera AI/ML environment. (DSE-42562)
Resolved an issue where users with the Team Admin role were unable to update team descriptions due to a permission mismatch. The system now correctly aligns the required permission levels, allowing team creators to manage their team settings as expected. (DSE-48770)

Cloudera AI Workbench

Increased file transfer timeouts to 10 minutes for uploads and 15 minutes for downloads, ensuring reliable API v2 transfer of large files. (DSE-39671)

Cloudera AI Inference service

NVIDIA optimized profiles for the following models are no longer supported and have been removed from the Model Hub in this release:
- Llama 3.2 11B
- Llama 3.2 90B
- Mixtral 8x22B
Although these optimized profiles are no longer available in the Model Hub, the models remain supported and accessible through Hugging Face.