Comment Comment by bjornsing > CUDA has been a huge moatThe CUDA moat is extremely exaggerated for deep learning, especially for inference. It’s simply not hard to do matrix multiplication and a few activation functions here and there. parent bjornsing 1 year ago
The CUDA moat is extremely exaggerated for deep learning, especially for inference. It’s simply not hard to do matrix multiplication and a few activation functions here and there.