[treksis]

how fast is this compare to python based?

[antirez]

Very slow currently, I added the benchmarks in the README. To go faster it needs to implement inference faster than the current float32-only kernels.

[rcarmo]

The Python libraries are themselves written in C/C++, so what this does performance-wise is, at best, cutting through some glue. Don't think about this as a performance-driven implementation.

[throwaway314155]

PyTorch MPS is about 10x faster per the README.md.

[antirez]

I cut the difference in speed by half by taking the activations on the GPU. Time to sleep but will continue tomorrow.

[Numerlor]

Have you tried e.g. Mojo that can vectorize/do SIMD without having to do intrinsics everywhere?