LaunchDevelopersAugust 24, 2026

llama.cpp 0.2.0 released with new docs home

Read original source →x.com

llama.cpp version 0.2.0 is out, with docs now hosted at llama.app/docs. Recent PRs add DFlash2 support, an --n-cpu-ffn option for low-VRAM dense models, and adaptive speculation for faster inference.

How this story unfolded

2 days · 0 reports · 3 community posts · from Aug 22

  1. Aug 22
  2. Aug 24

More stories today

Open the live feed