inari@piefed.zip to Technology@lemmy.worldEnglish · edit-21 day agoDeepSeek ditches Nvidia for Huawei chips in V4 launchcybernews.comexternal-linkmessage-square84fedilinkarrow-up1389
arrow-up1389external-linkDeepSeek ditches Nvidia for Huawei chips in V4 launchcybernews.cominari@piefed.zip to Technology@lemmy.worldEnglish · edit-21 day agomessage-square84fedilink
minus-squarebillwashere@lemmy.worldlinkfedilinkEnglisharrow-up3·10 hours agoSorry if this is a dumb question, but is this just for training or does DeepSeek v4 now require these chips to run?
minus-squareqaz@lemmy.worldlinkfedilinkEnglisharrow-up4·10 hours agoI don’t think they only run on these chips. There are some companies in the US that provide Deepseek V4 presumably running on standard Nvidia chips.
minus-squarebillwashere@lemmy.worldlinkfedilinkEnglisharrow-up3·9 hours agoWell I’ve got three 512gb Mac Studios in an EXO cluster I’m gonna see how it works.
minus-squarehumanspiral@lemmy.calinkfedilinkEnglisharrow-up2·9 hours agoIt is for inference, which is generally good at open backends. Most models done in pytorch, with backend library.
Sorry if this is a dumb question, but is this just for training or does DeepSeek v4 now require these chips to run?
I don’t think they only run on these chips. There are some companies in the US that provide Deepseek V4 presumably running on standard Nvidia chips.
Well I’ve got three 512gb Mac Studios in an EXO cluster I’m gonna see how it works.
It is for inference, which is generally good at open backends. Most models done in pytorch, with backend library.