Hybrid/cloud inference
The following is intended for informational purposes only, and may not be incorporated into any contract. No purchasing decisions should be made based on the following materials. Unity is not committing to deliver any functionality, features or code. The development, timing and release of all products, functionality and features are at the sole discretion of Unity, and are subject to change.
If you have accepted to use functional cookies and logged in using your Unity ID at the top right of the page, then sharing feedback is as simple as clicking a card below, selecting a topic’s importance, adding your point of view, and submitting. If you prefer not to accept functional cookies or log in, you will be prompted to enter an email address and validate it, so we know how to reach out when the topic evolves. For more information read the Feedback and privacy terms.
Ability for Unity runtime to “broker” AI model inference between local vs. cloud resources. This would be based on a real-time technical diagnostic including factors like the local compute/OS, frame rate (FPS), inference speed (ms), or network connection, where a “burst” to the cloud might be needed to maintain performance. It could also be based on business rules, such as a player LTV, budget, or player behavior. We would love to hear about the factors that would intelligently determine how an inference should be routed.