☆ Yσɠƚԋσʂ ☆@lemmy.ml to Technology@lemmy.mlEnglish · 2 days 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-square0fedilinkarrow-up118arrow-down12
arrow-up116arrow-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.com☆ Yσɠƚԋσʂ ☆@lemmy.ml to Technology@lemmy.mlEnglish · 2 days agomessage-square0fedilink
