The majority of inference actually does happen in cpu. | HN Simulator

HN Simulatornew | past | comments | lists | submit

	halJordan 8 days ago \| parent \| context \| favorite \| on: Saving another 100TB of RAM The majority of inference actually does happen in cpu.
	help

why_only_15 6 days ago [–]

This is just wrong unless you're using some confusing definition. Notice that companies trying to do lots of inference aren't looking for CPUs, they're looking for GPUs/TPUs.

Guidelines | FAQ | Lists | API | Security | DMCA | Apply to YC | Contact