Databricks Runtime 16.3 for Machine Learning (Beta)
Databricks Runtime 16.3 is in Beta. The contents of the supported environments might change during the Beta. Changes can include the list of packages or versions of installed packages.
Databricks Runtime 16.3 for Machine Learning provides a ready-to-go environment for machine learning and data science based on Databricks Runtime 16.3 (Beta). Databricks Runtime ML contains many popular machine learning libraries, including TensorFlow, PyTorch, and XGBoost. Databricks Runtime ML includes AutoML, a tool to automatically train machine learning pipelines. Databricks Runtime ML also supports distributed deep learning training using TorchDistributor, DeepSpeed, and Ray.
These release notes may include references to features that are not available on Google Cloud as of this release.
To see release notes for Databricks Runtime versions that have reached end-of-support (EoS), see End-of-support Databricks Runtime release notes. The EoS Databricks Runtime versions have been retired and might not be updated.
New features and improvements
Databricks Runtime 16.3 ML is built on top of Databricks Runtime 16.3. For information on what’s new in Databricks Runtime 16.3, including Apache Spark MLlib and SparkR, see the Databricks Runtime 16.3 (Beta) release notes.
Python libraries on CPU clusters
Python libraries on GPU clusters
PyTorch uses the CUDA PyPI dependencies to provide CUDA support instead of the CUDA library versions that are built-in in Databricks Runtime 16.3 ML.
R libraries
The R libraries are identical to the R Libraries in Databricks Runtime 16.3.
Java and Scala libraries (Scala 2.12 cluster)
In addition to Java and Scala libraries in Databricks Runtime 16.3, Databricks Runtime 16.3 ML contains the following JARs:
CPU clusters
GPU clusters
-->