Upgraded to MacOS 15, CoreML models is more slower

After I upgraded to MacOS 15 Beta 4(M1 16G), the sampling speed of apple ml-stable-diffusion was about 40% slower than MacOS 14.

And when I recompile and run with xcode 16, the following error will appear:

loc("EpicPhoto/Unet.mlmodelc/model.mil":2748:12): error: invalid axis: 4294967296, axis must be in range -|rank| <= axis < |rank|
Assertion failed: (0 && "failed to infer output types"), function _inferJITOutputTypes, file GPUBaseOps.mm, line 339.

I checked the macos 15 release notes and saw that the problem of slow running of Core ML models was fixed, but it didn't seem to be fixed.

  • Fixed: Inference time for large Core ML models is slower than expected on a subset of M-series SOCs (e.g. M1, M1 max) on macOS. (129682801)

update:

macOS 15 beta 5 fixes running errors after recompilation.

However, the problem of slowing down the running speed of the model is still not solved, especially the SDXL with flexible shape.

Hello @andykoko,

Please file a bug report for this issue using Feedback Assistant if you have not already!

Best regards,

Greg

Upgraded to MacOS 15, CoreML models is more slower
 
 
Q