AI’s hidden storage bill: What inference leaves behind

T1Covered by 1 source · first reported by MIT Technology Review at 22 Oct, 08:41 UTC

Ask most executives to picture the cost of AI and they’ll likely see GPUs—racks of accelerators with gigawatts of power—and a waitlist for silicon. But that picture leaves something out: Data storage costs. What happens to data after a model responds? Much of the back-end data that’s generated—from…

aihardware

Sources

• T1AI’s hidden storage bill: What inference leaves behindMIT Technology Review22 Oct, 08:41