Florian Bruggisser
Florian Bruggisser
It converts the models into the CoreML format and executes them, i.e. the available accelerators are used.
Thank you for the PR. Merging it into the main branch does not really make sense because the basic functionality of the script is not changed. But I can merge...
@henryruhs I have already pre-built the wheels and created a branch for it. No need for sending patch files manually around. What needs to be done is to test the...
@siyuzou As already mentioned in various other issues, performance depends a lot on your model. If your model uses unsupported layers, the runtime has to move the data from the...
I've just added a release for [v1.16.3](https://github.com/cansik/onnxruntime-silicon/releases/tag/v.1.16.3) built on MacOS 14. Maybe it fixes the issues you currently have?
@Oil3 Yes there is a list of supported operators, you can find them over [here](https://onnxruntime.ai/docs/execution-providers/CoreML-ExecutionProvider.html#supported-ops).
Ok great! I will have a look at it :)
Hi @kougaku, sorry for my late reply I just did not have the time to look into that until now. In general it is recommended to use `loadImage()` to load...
It seems that the issue is related to the [wgpu-py](https://github.com/pygfx/wgpu-py) package. I am not even sure why this has been added (https://github.com/pygfx/wgpu-py/commit/7dcd6aef343f0c811d41bceec3c892b311ac7507), it seems to it has been added to...
@Korijn I have created a PR to fix this in wgpu and another one which updates the wx example in pygfx. Would be great if you could have a look.