Sr Hpm
Fast decoding of dense LLMs larger than GPU memory on consumer hardware: llama.cpp patch + launcher (2.7 -> ~10 tok/s for a 27B model on a 6 GB laptop GPU)
BitsExplorer finds what people are building with AI, every day. See today's picks →
Unofficial Moon Sweepers fan tool: plan pressure chamber and stone press lines, test them, and share layouts as codes.
Description excerpted from the original listing, which is linked below.
Every Monday: how many projects were built with AI that week, which tools built them, where they came from, and the week's picks.
Read the latest week