Install this package:
emerge -a sci-misc/koboldcpp<pkgmetadata>
<maintainer type="person">
<email>iohann.s.titov@gmail.com</email>
<name>Ivan S. Titov</name>
</maintainer>
<longdescription>
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.
</longdescription>
<upstream>
<remote-id type="github">LostRuins/koboldcpp</remote-id>
</upstream>
</pkgmetadata>
Manage flags for this package:
euse -i <flag> -p sci-misc/koboldcpp |
euse -E <flag> -p sci-misc/koboldcpp |
euse -D <flag> -p sci-misc/koboldcpp
| Flag | Description | 1.117.1 | 1.116.1 |
|---|---|---|---|
| vulkan | Build the Vulkan llama-server GPU backend ⚠️ | ⊕ | ⊕ |
| Type | File | Size | Versions |
|---|---|---|---|
| DIST | koboldcpp-1.116.1.gh.tar.gz | 87638370 bytes | 1.116.1 |
| DIST | koboldcpp-1.117.1.gh.tar.gz | 87735168 bytes | 1.117.1 |
| Type | File | Size |
|---|