jaykrown@lemmy.world to Technology@lemmy.worldEnglish · 1 month agoDeepSeek Permanently Reduces The Price Of Its Flagship V4 Model By 75 Percenttech.yahoo.comexternal-linkmessage-square138linkfedilinkarrow-up11arrow-down10
arrow-up11arrow-down1external-linkDeepSeek Permanently Reduces The Price Of Its Flagship V4 Model By 75 Percenttech.yahoo.comjaykrown@lemmy.world to Technology@lemmy.worldEnglish · 1 month agomessage-square138linkfedilink
minus-squareTja@programming.devlinkfedilinkEnglisharrow-up0·1 month agoHow are they running it? Doesn’t the model have to fit in (V)RAM? Does Nvidia have such huge memories in the H cards?
minus-squareBlackLaZoR@lemmy.worldlinkfedilinkEnglisharrow-up0·1 month agoThere’s tech for splitting model to run on multiple cards, but it requires really fast interconnect between GPUs.
minus-squareTaasz/Woof@lemmy.blahaj.zonelinkfedilinkEnglisharrow-up0·1 month agoLots of GPUs together.
How are they running it? Doesn’t the model have to fit in (V)RAM? Does Nvidia have such huge memories in the H cards?
There’s tech for splitting model to run on multiple cards, but it requires really fast interconnect between GPUs.
Lots of GPUs together.