"Rubin is an AI supercomputing platform designed to make "building, deploying, and securing the world's largest and most advanced AI systems at the lowest cost" possible. According to Nvidia, the platform can deliver up to a 10x reduction in inference token costs and requires four times fewer graphics cards to train mixture-of-experts (MoE) models compared to the older Blackwell platform."
"The goal with Rubin is to accelerate mainstream adoption of advanced AI models, particularly in the consumer space. One of the biggest hurdles holding back widespread adoption of LLMs is cost. As models grow larger and more complex, the hardware and infrastructure required to train and support the models become astronomically expensive. By sharply reducing those token costs via Rubin, Nvidia hopes to make large-scale AI deployment more practical."
Rubin is an AI supercomputing platform designed to make "building, deploying, and securing the world's largest and most advanced AI systems at the lowest cost" possible. The platform can deliver up to a 10x reduction in inference token costs and requires four times fewer graphics cards to train mixture-of-experts (MoE) models compared to the older Blackwell platform. Rubin expands on Blackwell at much larger scale and uses an "extreme codesign" approach to create a single AI supercomputer. The platform targets mainstream consumer adoption by lowering infrastructure costs and aims to roll out initial platforms to partners later in the year. The cost reductions seek to make large-scale AI deployment more practical.
Read at ZDNET
Unable to calculate read time
Collection
[
|
...
]