Someone really needed a few hundred TB to waste on inference and went looking under the rugs…

CPU DRAM can't really be used for inference efficiently -- inference mostly wants memory bandwidth, not memory capacity, and GPU DRAM has >10x more bandwidth. The fabs can switch between them but you can't switch after the fact.

	▲	sroussey 4 hours ago \| parent \| next [-]
		Those machines with GPUs still need RAM of their own, and they generally want large caches to avoid SSD penalties. You even see this spill out in the form of costs for KV cache in <1min, 5m, 1hr rates etc.
	▲	halJordan 3 hours ago \| parent \| prev [-]
		The majority of inference actually does happen in cpu.