Is there a way to pin arrays in Numba, for fast data transfer to/from device?

Question

In Pytorch, there is an option to pin CPU arrays for fast transfer to GPU (does not seem to work for GPU -> CPU though).

I am wondering if there is a way to pin Numba arrays to memory, or any alternative technique for fast transfer from CPU to GPU. I do not see a direct option for this from the documentation, so my guess is that we need to specify allocation during the array creation.