Skip to main content
Version: 1.49

1.42.0

Release notes​

✨ New features​

  • Assign a risk classification to your Deployment
    Assign a risk classification that denotes the risk of your machine learning application according to the EU AI Act risk classification.

  • Added support for batch explanations
    Request batch explanations just like batch predictions, generating individual prediction logs for easy tracking.

🛠️ Improvements​

  • Updated Kserve version to v0.13.1
  • Improved metadata parsing error handling
  • Improved error handling and usability of blob credentials
  • Improved performance (reduced latency) of inference endpoints
  • Added an installation status page for Enterprise users

🐛 Bug fixes​

  • Fixed issue of visible deleted deployments in team overview
  • Fixed stuck deployment on invalid repository, branch name or commit
  • Fixed the formatting of errors in the alert rule dialog
  • Fixed an issue where auto scaling seemed to be removed in the Deployment summary
  • Fixed an issue where a team admin appeared to have no workspaces
  • Archiving Azure Machine Learning Deployments now behaves correctly