Why does CUDA MPS always occupy the same size of memory?

AI & Data Science Data Processing
1

I turned on MPS on Tesla T4 and found that MPS turned on and not turned on, the GPU Memory Usage on NVIDIA-SMI is the same.
Q1：Does MPS work?
Q2：Why the GPU Memory Usage occupied by CUDA programs is the same？
Q3：Why MPS Server always occupies 25Mib？I tested other applications with MPS turned on, it also takes 25Mib in NVIDIA-SMI, but I forgot to save the result.

image
image1471×663 156 KB

image2022-5-15_9-25-53
image2022-5-15_9-25-531274×628 103 KB

Best，
Lucas

2

mps server always take 25MB. I guess you want to save some GPU memory by using MPS， but context itself may just consume a small part of the memory?