jaykrown@lemmy.world to Technology@lemmy.worldEnglish · 12 hours agoDeepSeek Permanently Reduces The Price Of Its Flagship V4 Model By 75 Percenttech.yahoo.comexternal-linkmessage-square83linkfedilinkarrow-up1340arrow-down111
arrow-up1329arrow-down1external-linkDeepSeek Permanently Reduces The Price Of Its Flagship V4 Model By 75 Percenttech.yahoo.comjaykrown@lemmy.world to Technology@lemmy.worldEnglish · 12 hours agomessage-square83linkfedilink
minus-squareTja@programming.devlinkfedilinkEnglisharrow-up1·2 hours 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-up1·1 minute 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-up1·2 minutes agoLots of GPUs together.
minus-squareboonhet@sopuli.xyzlinkfedilinkEnglisharrow-up1·edit-236 minutes agoFor self hosting it essentially needs to fit in VRAM + RAM but it’ll take a lot of CPU for the part in RAM Deepseek probably uses those big fancy H cards and not one but several together to increase VRAM.
FYI the flash model is ~158 GB
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.
For self hosting it essentially needs to fit in VRAM + RAM but it’ll take a lot of CPU for the part in RAM
Deepseek probably uses those big fancy H cards and not one but several together to increase VRAM.
The destiled models?