Comment on Microsoft 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.

<- View Parent
Dojan@pawb.social ⁨6⁩ ⁨days⁩ ago

We already have that. It’s like, you put the AI in your brain. You are the AI.

source
Sort:hotnewtop