Gentoo Packages

Category: sci-misc

• sci-misc/koboldcpp::stuff - Ebuilds: 2, Testing: 1.117.1
  Description: KoboldCpp is a single-binary local AI server built on ggml/llama.cpp that bundles LLM text generation (KoboldAI Lite web UI + an OpenAI-compatible API), Stable Diffusion image generation, Whisper speech-to-text and TTS. This ebuild builds the ggml backends from source and installs the pure-Python launcher (koboldcpp.py) with the embedded web UI and resources; it does NOT ship the upstream PyInstaller binary or any model weights. AMD/NVIDIA GPU acceleration is via Vulkan (the officially supported path); ROCm/hipBLAS is best-effort.
  Homepage: https://github.com/LostRuins/koboldcpp
  License: AGPL-3+ MIT
• sci-misc/llama-cpp::stuff - Ebuilds: 3, Testing: 0_pre9951, Snapshot: 9999
  Description: Port of Facebook's LLaMA model in C/C++
  Homepage: https://github.com/ggml-org/llama.cpp
  License: MIT
• sci-misc/llama-swap::stuff - Ebuilds: 2, Testing: 238
  Description: llama-swap is an OpenAI/Anthropic-compatible HTTP proxy that starts and stops local LLM inference servers (llama.cpp, vllm, mlx-server, etc.) on demand based on the requested model. Lets a single API endpoint serve many models without keeping them all resident in GPU/NPU memory.
  Homepage: https://github.com/mostlygeek/llama-swap
  License: MIT
• sci-misc/stable-diffusion-cpp::stuff - Ebuilds: 3, Testing: 0_pre769, Snapshot: 9999
  Description: Diffusion model (SD, Flux, Wan, Qwen-Image, ...) inference in pure C/C++
  Homepage: https://github.com/leejet/stable-diffusion.cpp
  License: MIT