You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I read that onnx runtime v1.19.4 supports acceleration for Apple Silicon. I assume this means GPU support is now available for the M1 chip. I can't find any examples of how to specify an M1 gpu in onnx runtime.
If I specify print(ort.get_device()), it will show me a CPU device.
If I try to install onnxruntime-gpu, it can't find a version. I think this is the wrong approach, as onnxruntme-gpu refers to CUDA only.
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
I read that onnx runtime v1.19.4 supports acceleration for Apple Silicon. I assume this means GPU support is now available for the M1 chip. I can't find any examples of how to specify an M1 gpu in onnx runtime.
If I specify
print(ort.get_device())
, it will show me a CPU device.If I try to install onnxruntime-gpu, it can't find a version. I think this is the wrong approach, as onnxruntme-gpu refers to CUDA only.
Beta Was this translation helpful? Give feedback.
All reactions