On the radar·Experiments·since 2026 Preview

AI Runtime

Serverless GPU compute with a distributed decorator for PyTorch, DeepSpeed and Ray workloads.

Why it is worth watching

The replacement for Foundation Model Fine-tuning, which has reached end of life.

What Public Preview promises

Open to everyone and supported for production use, though it can still change. On by default, and an admin can turn it off.

Who can use itEveryone
Production useYes
SupportThe support team
On by defaultYes, with an opt-out

The definitions are Databricks' own, on its release types page. The label on this page is the one the feature's documentation states, last checked on 14 Sept 2026.

Where to read more

We wrote it up: AI Runtime and serverless GPU compute — Serverless GPU compute for training and fine-tuning: a @distributed decorator in notebooks, the air CLI with a workload YAML, and the successor to Foundation Model Fine-tuning. That page carries the Public Preview label while this entry does.

The Databricks documentation for AI Runtime

Newsletter

Hear when AI Runtime changes label

We re-read the documentation behind every preview and tell you when a label moves, or when a feature quietly disappears.

Choose what you get5 of 15

Each one is a section of the letter, and you only get the ones you tick. Every email carries a link back to this list, so you can change it later without an account.

Double opt-in: we send one email to check the address is yours. Nothing else until you confirm.