The current workflow does not allow for the uses of AMD gpu's with ROCM, as there is no good support for gpu based numba. I have added a ROCM workflow to the code, let me know if you're interested and I'll create a branch.
The current workflow does not allow for the uses of AMD gpu's with ROCM, as there is no good support for gpu based numba.
I have added a ROCM workflow to the code, let me know if you're interested and I'll create a branch.