I used MPS on GTX1050…1070 boards and faced a limitation of 16 connection that well noticed in manual:
The pre-Volta MPS Server supports up to 16 client CUDA contexts per-device
concurrently. Volta MPS server supports 48 client CUDA contexts per-device.
Does RTX 2060 that is Turing supports 48 or 16 client CUDA contexts?