NVIDIA and Google infrastructure cuts AI inference costs
Google ve NVIDIA, AI çıkarım maliyetlerini düşürmek için yeni A5X bare-metal instance'ları ve NVIDIA Vera Rubin NVL72 sistemlerini tanıttı. Donanım-yazılım ortak tasarımı ile on kat daha düşük maliyet hedefleniyor.
Google Cloud and NVIDIA have announced a new hardware infrastructure aimed at significantly reducing the expenses associated with large-scale artificial intelligence inference. The companies revealed the upcoming A5X bare-metal instances, which will be powered by NVIDIA's Vera Rubin NVL72 rack-scale systems. This collaborative approach, involving both hardware and software co-design, is projected to offer a tenfold decrease in inference costs.
This development is significant as it addresses a major bottleneck in deploying AI applications widely, potentially making advanced AI services more accessible and affordable.
📌 Kaynak
Bu özet artificialintelligence kaynağından otomatik derlenmiştir. Tamamı için orijinal habere gidin.
Orijinal haberi oku →