Lee Duna@lemmy.nz to Technology@beehaw.orgEnglish · 11 months agoApple wants AI to run directly on its hardware instead of in the cloudarstechnica.comexternal-linkmessage-square35fedilinkarrow-up1113arrow-down10cross-posted to: technology@lemmy.worldhackernews@lemmy.smeargle.fanshackernews@derp.foo
arrow-up1113arrow-down1external-linkApple wants AI to run directly on its hardware instead of in the cloudarstechnica.comLee Duna@lemmy.nz to Technology@beehaw.orgEnglish · 11 months agomessage-square35fedilinkcross-posted to: technology@lemmy.worldhackernews@lemmy.smeargle.fanshackernews@derp.foo
minus-squareKevin Herrera@beehaw.orglinkfedilinkEnglisharrow-up5·11 months agoApple added (a while back) what they call a “Neural Engine,” which is hardware dedicated to efficient execution of ML workloads. https://en.m.wikipedia.org/wiki/Apple_A11 They have been refining it ever since. I would not be surprised if they made advancements in both the hardware and software used for local GAI.
minus-squarejmcslinkfedilinkarrow-up2·11 months agoAnd Google did the same with the Tensor Processor Unit in the Pixels.
Apple added (a while back) what they call a “Neural Engine,” which is hardware dedicated to efficient execution of ML workloads.
https://en.m.wikipedia.org/wiki/Apple_A11
They have been refining it ever since. I would not be surprised if they made advancements in both the hardware and software used for local GAI.
And Google did the same with the Tensor Processor Unit in the Pixels.