{"id":"4c107937-c5bb-43cb-9d66-bed0f900f917","url":"https://api.tumn.com/news/4c107937-c5bb-43cb-9d66-bed0f900f917","title":"Memory-Enforced GPU Sharing in Kubernetes with NVIDIA CUDA 13.4","summary":"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...","sections":[],"faq":[],"sources":[{"url":"https://developer.nvidia.com/blog/memory-enforced-gpu-sharing-in-kubernetes-with-nvidia-cuda-13-4/","title":"NVIDIA Developer Blog","publishedAt":"2026-10-27T20:50:39.000Z"}],"author":"TUMN 큐레이션","aiAssisted":false,"reviewStatus":"automated","reviewNote":"원문 제목과 공개된 발췌를 인용하고 원문으로 연결합니다. 내용을 재작성하거나 요약하지 않았습니다.","publishedAt":"2026-10-27T20:50:39.000Z","modifiedAt":"2026-10-28T03:26:27.000Z","checkedAt":"2026-10-28T03:26:27.628Z","language":"ko","kind":"link","sourceLabel":"AI 공식","profile":null,"via":null,"formats":{"json":"https://api.tumn.com/news/4c107937-c5bb-43cb-9d66-bed0f900f917.json","markdown":"https://api.tumn.com/news/4c107937-c5bb-43cb-9d66-bed0f900f917.md"}}