[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-vera-rubin-nvl72":3},{"tag":4,"articles":11},{"id":5,"name":6,"slug":7,"article_count":8,"description_zh":9,"description_en":10},"ae4d5468-947a-4b58-80d0-1357e6c887a9","Vera Rubin NVL72","vera-rubin-nvl72",3,"Vera Rubin NVL72 是 NVIDIA 以機櫃為單位設計的 AI 基礎設施平台，將 GPU、CPU、DPU、網路與交換器整合成一套系統，重點在推論成本、MoE 訓練效率與雲端部署規模。","Vera Rubin NVL72 is NVIDIA’s rack-scale AI system built around the Rubin platform, combining GPUs, CPUs, DPU, networking, and switches. It matters because it targets lower inference cost, more efficient MoE training, and deployment at cloud and enterprise scale.",[12],{"id":13,"slug":14,"title":15,"summary":16,"category":17,"image_url":18,"cover_image":18,"language":19,"created_at":20},"45da1b55-3f7d-49d6-a7fa-be0f503dcd3a","nvidia-rubin-ai-infrastructure-2026-en","NVIDIA Rubin Pushes AI Infrastructure to a New Scale","NVIDIA’s Rubin platform bundles six chips, claims 10x lower inference cost, and brings Vera Rubin NVL72 systems to cloud and enterprise AI.","industry","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1774497418478-ye2x.png","en","2026-03-30T06:18:53.417098+00:00"]