Popular repositories Loading

1. airunner airunner Public

   Local model runner manager: launch, manage, watch, and auto-restart GGUF models via llama.cpp (llama-server) and DwarfStar (ds4-server). Zero-dependency Python 3 stdlib backend + single-page vanill…

   Python 1

2. strix-halo-llamacpp strix-halo-llamacpp Public

   Forked from Nathanw1014/llama.cpp

   LLM inference in C/C++

   C++ 1