ooli@lemmy.world to Technology@lemmy.worldEnglish · 7 months agoGPU's rival? What is Language Processing Unit (LPU)www.turingpost.comexternal-linkmessage-square13fedilinkarrow-up194arrow-down19
arrow-up185arrow-down1external-linkGPU's rival? What is Language Processing Unit (LPU)www.turingpost.comooli@lemmy.world to Technology@lemmy.worldEnglish · 7 months agomessage-square13fedilink
minus-squareScott@sh.itjust.workslinkfedilinkEnglisharrow-up2·7 months agoIt’s not about their frontend, they are running custom LPUs which can process LLM tokens at 500/sec which is insanely impressive. For reference with a max size of 2k tokens, my dual xeon silver 4114 procs take 2-3 minutes.
minus-squareLojcs@lemm.eelinkfedilinkEnglisharrow-up1·7 months agoNo I got what you meant, but that site is weird if it’s not doing anything on its own
minus-squareFinadil@lemmy.worldlinkfedilinkEnglisharrow-up1·7 months agoThat with a fp16 model? Don’t be scared to try even a 4 bit quantization, you’d be surprised at how little is lost and how much quicker it is.
It’s not about their frontend, they are running custom LPUs which can process LLM tokens at 500/sec which is insanely impressive.
For reference with a max size of 2k tokens, my dual xeon silver 4114 procs take 2-3 minutes.
No I got what you meant, but that site is weird if it’s not doing anything on its own
That with a fp16 model? Don’t be scared to try even a 4 bit quantization, you’d be surprised at how little is lost and how much quicker it is.