CoreML Unified Memory failure/silent exit on long video tasks (M1 Mac 32GB)

Machine Learning & AI Core ML
Chr1230 OP
Created 3h
Replies 0
Boosts 0
Views 6
Participants 1

Hi Apple Engineers,

I am experiencing a potential memory management bug with CoreML on M1 Mac (32GB Unified Memory).

When processing long video files (approx. 12,000 frames) using a CoreML execution provider, the system often completes the 'Analysing' phase but fails to transition into 'Processing'. It simply exits silently or hits an import error (scipy).

However, if I split the same task into small 20-frame segments, it works perfectly at high speeds (~40 FPS). This suggests the hardware is capable, but there is an issue with memory fragmentation or resource cleanup during long-running CoreML sessions.

Is there a way to force a VRAM/Unified Memory flush via CLI, or is this a known limitation for large frame indexing?

Replies  0
Boosts  0
Views  6
Participants  1
CoreML Unified Memory failure/silent exit on long video tasks (M1 Mac 32GB)
First post date Last post date
 
 
Q