한국어EN
On-Device & Local InferenceGeorgi Gerganov

Georgi Gerganov starts developing llama.cpp

Made by AIWritten by AI (Claude) from the source below. Check anything important against the source.How it's made

Started developing llama.cpp — Llama inference implemented in pure C/C++ with no dependencies

Why it matters

Spread among users without dedicated hardware. Being able to run on a CPU alone was decisive

Source — Primary sources first; secondary reports are labelled “Press”

Pressen.wikipedia.orghttps://en.wikipedia.org/wiki/Llama.cpp

Added in Week 35, 2026 · See that week

On the map — ⑲ On-Device line

  1. Previous stopGPTQ
  2. This record · stopllama.cpp
  3. Next stopPhi-3
See it on the map

Nearby on the same axis

Frantar et al. present GPTQPaperggml project introduces the GGUF (GGML Universal File) formatPressDettmers et al. present LLM.int8()PaperMicrosoft Research publishes Phi-3 technical reportPaper