NVIDIA CUDA 13.4 如何在 Kubernetes 中实现内存强制的 GPU 共享
Memory-Enforced GPU Sharing in Kubernetes with NVIDIA CUDA 13.4
NVIDIA CUDA 13.4 支持在 Kubernetes 中对 GPU 进行内存强制隔离的共享，让多个 AI 工作负载共用同一块 GPU。NVIDIA GPU 已支持多种共享方式，其中 MIG 可将 GPU 拆分为对应用透明的硬件隔离实例。该能力面向平台团队，用现有基础设施承载更多工作负载。
Many AI workloads need only a fraction of a GPU. Giving each one an entire device can leave capacity idle; sharing GPUs lets platform teams serve more workloads...
Many AI workloads need only a fraction of a GPU. Giving each one an entire device can leave capacity idle; sharing GPUs lets platform teams serve more workloads with the infrastructure they already have. NVIDIA GPUs already support several approaches to sharing. Multi-instance GPU (MIG) splits a GPU into hardware-isolated instances that are transparent to the application…
来源：NVIDIA Technical Blog · developer.nvidia.com