Inference Infrastructure & ServingGeorgi Gerganov
Georgi Gerganov creates the llama.cpp repository
Created the llama.cpp repository
Why it matters
Dependency-free inference in pure C/C++ opened the way to running LLMs on a laptop without a GPU
Source — Primary sources first; secondary reports are labelled “Press”
Officialapi.github.comhttps://api.github.com/repos/ggml-org/llama.cppAdded in Week 35, 2026 · See that week