graph TD;
ggml --> whisper.cpp
ggml --> llama.cpp
llama.cpp --> llama.vim
llama.cpp --> llama.vscode
ggml[<a href="https://.com/ggml-org/ggml" style="text-decoration:none;">ggml</a> <br><span style="font-size:10px;">Machine learning library</span>];
whisper.cpp[<a href="https://.com/ggml-org/whisper.cpp" style="text-decoration:none;">whisper.cpp</a> <br><span style="font-size:10px;">speech-to-text</span>];
llama.cpp[<a href="https://.com/ggml-org/llama.cpp" style="text-decoration:none;">llama.cpp</a> <br><span style="font-size:10px;">LLM inference</span>];
llama.vim[<a href="https://.com/ggml-org/llama.vim" style="text-decoration:none;">llama.vim</a> <br><span style="font-size:10px;">Vim/Neovim plugin</span>];
llama.vscode[<a href="https://.com/ggml-org/llama.vscode" style="text-decoration:none;">llama.vscode</a> <br><span style="font-size:10px;">VSCode plugin</span>];
[2025 May 08]LM Studio Accelerates LLM Performance With NVIDIA GeForce RTX GPUs and CUDA 12.8[2025 Apr 18]Gemma 3 QAT Models: Bringing state-of-the-Art AI to consumer GPUs[2025 Apr 16]Llama 4 Runs on Arm[2025 Apr 04]Run LLMs Locally with Docker[2025 Mar 25]Deploy a Large Language Model (LLM) chatbot with llama.cpp using KleidiAI on Arm servers[2025 Feb 11]OLMoE, meet iOS[2024 Oct 02]Accelerating LLMs with llama.cpp on NVIDIA RTX Systems
ggml/llama.cppmaintainer, full-timeapply at [email protected] (only active contributors will be considered)