Is there a way to tell a cuda application to not communicate with MPS server? (multi gpu system)

Hi Cuda/MPS team,
I have a 2 gpus on my system.
I have enabled MPS server setting CUDA_VISIBLE_DEVICES=0 which means only 1 gpu is used by MPS.

I want to run a few related applications on GPU 0 which is controlled by MPS.

And I want to run another unrelated application on the other GPU i.e. gpu 1 which is not controlled by MPS. However, i see that the application gets intercepted by MPS server thus running on GPU0.
Is there a way to tell a cuda application to not communicate with MPS server?

Thank you.

Not that I know of. One possible approach would be to have all GPUs be mapped by MPS, and then have your application select the GPU it wants to run on.