Could not initialize NNPACK! Reason: Unsupported hardware.

[alelordelo]

Thanks Apple ML team for this!

I got this warning: Could not initialize NNPACK! Reason: Unsupported hardware.

Is this expected?

Torch version 1.13.0 has not been tested with coremltools. You may run into unexpected errors. Torch 1.12.1 is the most recent version that has been tested. !!! macOS 13.1 and newer or iOS/iPadOS 16.2 and newer is required for best performance !!! INFO:main:Initializing StableDiffusionPipeline with stabilityai/stable-diffusion-2-base.. Fetching 12 files: 100%|█████████████████████| 12/12 [00:00<00:00, 10409.85it/s] INFO:main:Done. INFO:main:Converting vae_decoder [W NNPACK.cpp:53] Could not initialize NNPACK! Reason: Unsupported hardware. /usr/local/Caskroom/miniforge/base/envs/coreml_stable_diffusion/lib/python3.8/site-packages/diffusers/models/resnet.py:109: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs! assert hidden_states.shape[1] == self.channels /usr/local/Caskroom/miniforge/base/envs/coreml_stable_diffusion/lib/python3.8/site-packages/diffusers/models/resnet.py:122: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs! if hidden_states.shape[0] >= 64:

[joaorafaelm]

same for me, and I installed torch==1.12.1, same error

[vlsalsa]

same here. Torch 1.13.0 though.

[JakubMazur]

anyone figured this out? same issue same versions

[YangSuoly]

Torch 1.13.1 and Venture 13.2.1 on Mac, same issue for me, any solution for this problem?

[gschian0]

I am getting this error too.... should we just wait ?