SoftestSapphic@lemmy.world to 196@lemmy.world · 3 days ago"AI" rulelemmy.worldimagemessage-square85fedilinkarrow-up1684arrow-down153
arrow-up1631arrow-down1image"AI" rulelemmy.worldSoftestSapphic@lemmy.world to 196@lemmy.world · 3 days agomessage-square85fedilink
minus-squareBlaster M@lemmy.worldlinkfedilinkEnglisharrow-up23·3 days agoSo that assumes AI requests use 100 percent of the hardware 100 percent of the time.
minus-squareJohnDClay@sh.itjust.workslinkfedilinkarrow-up14arrow-down1·edit-23 days agoYes, but those servers are pretty ai specific, so that’s a decent assumption. Looks like Nvidia is drastically ramping up production of these servers, so current electricity use might be about 10x, I’m working on it.
minus-squareGissaMittJobb@lemmy.mllinkfedilinkarrow-up1·1 day ago100% utilization 100% of the time? That seems like an unlikely figure, right?
minus-squareJohnDClay@sh.itjust.workslinkfedilinkarrow-up2·1 day ago100% utilization yes, but server uptimes are in the 99 percent range.
minus-squareGissaMittJobb@lemmy.mllinkfedilinkarrow-up1·1 day agoIdle consumption vs full utilization consumption are two very different things, though - this will have a large impact on the final number.
So that assumes AI requests use 100 percent of the hardware 100 percent of the time.
Yes, but those servers are pretty ai specific, so that’s a decent assumption. Looks like Nvidia is drastically ramping up production of these servers, so current electricity use might be about 10x, I’m working on it.
100% utilization 100% of the time? That seems like an unlikely figure, right?
100% utilization yes, but server uptimes are in the 99 percent range.
Idle consumption vs full utilization consumption are two very different things, though - this will have a large impact on the final number.