Source item
Open original source ↗Inference demand is exploding - Jensen says about to 1 billion X as the result of agents & reasoning models. The new hot thing - dedicated, at scale inference clouds with custom silicon to help the largest consumers of tokens help meet that demand - fast & cheap. 🇺🇸🔥
Quoted context
These are the quoted author’s words.
A few weeks ago @cerebras announced that we be deploying our CS-3s in new data centers across the US. Below is a pic of our massive new deployment in Minneapolis. Serving inference from US based data centers at hyperscale capacity is the goal. https://t.co/CLrf9ex2gT
andrewdfeldman ↗