filister@lemmy.world to Technology@lemmy.worldEnglish · 1 年前DeepSeek R1 Is Reportedly Running Inference On Huawei's Ascend 910C AI Chips, Showing China's Growing AI Capabilitieswccftech.comexternal-linkmessage-square13fedilinkarrow-up1153arrow-down15
arrow-up1148arrow-down1external-linkDeepSeek R1 Is Reportedly Running Inference On Huawei's Ascend 910C AI Chips, Showing China's Growing AI Capabilitieswccftech.comfilister@lemmy.world to Technology@lemmy.worldEnglish · 1 年前message-square13fedilink
minus-squareaaron@lemm.eelinkfedilinkEnglisharrow-up1arrow-down43·1 年前I’m not going to parse this shit article. What does interference mean here? Please and thank you.
minus-squarefilister@lemmy.worldOPlinkfedilinkEnglisharrow-up42·1 年前That’s a very toxic attitude. Inference is in principle the process of generation of the AI response. So when you run locally and LLM you are using your GPU only for inference.
minus-squareaaron@lemm.eelinkfedilinkEnglisharrow-up24arrow-down7·1 年前Yeah, I misread because I’m stupid. Thanks for replying, non-toxic man.
minus-squareRobotToaster@mander.xyzlinkfedilinkEnglisharrow-up13·1 年前Inference? It’s the actual running of the ai when you use it, as opposed to training.
minus-squareaaron@lemm.eelinkfedilinkEnglisharrow-up13arrow-down2·1 年前Sorry. I forgot to mention that I’m dumb.
I’m not going to parse this shit article. What does interference mean here? Please and thank you.
That’s a very toxic attitude.
Inference is in principle the process of generation of the AI response. So when you run locally and LLM you are using your GPU only for inference.
Yeah, I misread because I’m stupid. Thanks for replying, non-toxic man.
deleted by creator
Inference? It’s the actual running of the ai when you use it, as opposed to training.
Sorry. I forgot to mention that I’m dumb.