Memory-Enforced GPU Sharing in Kubernetes with NVIDIA CUDA 13.4
Multi-instance GPU (MIG) splits a GPU into hardware-isolated instances that are transparent to the application, time-slicing lets several processes take turns without memory enforcement, and Multi-Process Service (MPS) lets them run concurrently in separate address spaces (sm-sharing).
CUDA 13.4 now enforces a memory boundary that is transparent to the application with a new time-sharing mode, alongside the compute sharing mode (sm-sharing) that already existed in MPS.
