cm0002@ttrpg.network to Technology@lemmy.zipEnglish · 2 months agoMicrosoft just open-sourced bitnet.cpp, a 1-bit LLM inference framework. It let's you run 100B parameter models on your local CPU without GPUs. 6.17x faster inference and 82.2% less energy on CPUs.github.comexternal-linkmessage-square5linkfedilinkarrow-up129arrow-down16cross-posted to: technology@hexbear.net
arrow-up123arrow-down1external-linkMicrosoft just open-sourced bitnet.cpp, a 1-bit LLM inference framework. It let's you run 100B parameter models on your local CPU without GPUs. 6.17x faster inference and 82.2% less energy on CPUs.github.comcm0002@ttrpg.network to Technology@lemmy.zipEnglish · 2 months agomessage-square5linkfedilinkcross-posted to: technology@hexbear.net
minus-squareLeon@pawb.sociallinkfedilinkEnglisharrow-up3arrow-down2·2 months agoWe already have that. It’s like, you put the AI in your brain. You are the AI.
We already have that. It’s like, you put the AI in your brain. You are the AI.