On Performance & Backgrounding

Machine Learning & AI Foundation Models
progressneverstops OP
Created 1d
Replies 1
Boosts 0
Views 18
Participants 2
This post is from the WWDC26 Foundation Models Q&A.

While we now know about the continued-processing.gpu entitlement for background tasks, is there a similar NPU-specific entitlement or priority flag to ensure that an on-device foundation model isn't preempted by system-level Apple Intelligence features while the app is in the background?

Answered by Frameworks Engineer in 892975022

The OS manages the requests for the on-device LLM automatically, based on the system conditions (like thermals). There's no entitlement or API to influence this.

Replies  1
Boosts  0
Views  18
Participants  2
Frameworks Engineer OP
Apple
1d
Recommended

The OS manages the requests for the on-device LLM automatically, based on the system conditions (like thermals). There's no entitlement or API to influence this.

On Performance & Backgrounding
First post date Last post date
 
 
Q