According to Nvidia, the chip, designed to be used in large data centers, offers 20 PetaFLOPS of AI performance that's 4x faster on AI-training workloads, 30x faster on AI-inferencing workloads and up to 25x more power efficient than its predecessor. The post Nvidia Raises Ante in AI Chip Game With New Blackwell Architecture appeared first on TechNewsWorld.
from TechNewsWorld https://ift.tt/9IitwKA
from TechNewsWorld https://ift.tt/9IitwKA
Comments
Post a Comment