Samuel Kemp
Samuel Kemp
This is similar issue to #130 and #134 where we need better handling of the device memory and then pulling the right model. In this case if the GPU memory...
Duplicate of #116 #91 #142
Thanks for raising an issue @ZhangWei125521! Currently, we do not expose a mechanism to select an execution provider (CUDA, Intel, AMD) for a given device.
This will be part of the WinML work.