Cloudera Docs

December 17, 2025

Release notes and fixed issues for version 2.0.53-b273.

New Features / Improvements

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
  • Added Non-Transparent Proxy (NTP) support. (DSE-39437)

Fixed Issues

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)

Behavioral Change

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)

Deprecation Notice

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.