Georgi Gerganov
3 mentions across all digests
Georgi Gerganov is the creator of llama.cpp and leads the GGML team, which joined Hugging Face to advance open-source local AI inference tooling while remaining fully open-source and community-driven.
Stop Using Ollama
Ollama, the dominant local LLM platform, systematically violated MIT licensing, abandoned open-source principles for VC funding, and degraded performance — with llama.cpp achieving 1.8× faster benchmarks after forking away.
Quoting Georgi Gerganov
Local LLMs fail for coding agents not due to raw capability but because fragmented architecture across chat templates, prompt construction, harness quirks, and inference creates cascading reliability issues throughout the stack.
GGML and llama.cpp join HF to ensure the long-term progress of Local AI