This package provides utility binaries for paraller general purpose computing use cases with the NVIDIA Server Driver.

CUDA MPS is a feature that allows multiple CUDA processes to share a single GPU context. CUDA MPS should be transparent to CUDA programs.

CUDA MPS requires a device that supports Unified Virtual Address (UVA) and has compute capability SM 3.5 or higher. Pre-CUDA 4.0 APIs are not supported under CUDA MPS.