gpo.zugaina.org

Search Portage & Overlays:

sci-misc/koboldcpp

All-in-one local AI server (LLM, image, speech, TTS) on ggml/llama.cpp

Screenshots

  • koboldcpp-1.117.1
    ~amd64
    +vulkan python_single_target_python3_12 python_single_target_python3_13 python_single_target_python3_14

    View      Download      Browse     License: AGPL-3+ MIT   
    Overlay: stuff
  • koboldcpp-1.116.1
    ~amd64
    +vulkan python_single_target_python3_12 python_single_target_python3_13 python_single_target_python3_14

    View      Download      Browse     License: AGPL-3+ MIT   
    Overlay: stuff

ChangeLog

commit 0ea4bf02868534a53d6e24f684529d59208f8eb7
Author: Ivan S. Titov <iohann.s.titov@gmail.com>
Date: Fri Jul 10 22:54:41 2026 +0200

sci-misc/koboldcpp: drop 1.117

commit 3275ff6d8959092a7865a79391b5ff8563c19cd5
Author: Ivan S. Titov <iohann.s.titov@gmail.com>
Date: Fri Jul 10 22:52:50 2026 +0200

sci-misc/koboldcpp: add 1.117.1

commit dd92dbbf146f61c83abc99580e261895dd7142c1
Author: Ivan S. Titov <iohann.s.titov@gmail.com>
Date: Fri Jul 10 15:24:51 2026 +0200

sci-misc/koboldcpp: add 1.117

commit 7f5741cf5ac46ac8a8b76539f7711aef7d274b21
Author: Ivan S. Titov <iohann.s.titov@gmail.com>
Date: Sat Jul 4 12:59:33 2026 +0200

sci-misc/koboldcpp: new package, add 1.116.1

All-in-one local AI server (LLM + Stable Diffusion + Whisper + TTS) built on
ggml/llama.cpp. Builds the ggml backends from the vendored source and installs
the pure-stdlib launcher (koboldcpp.py) with the embedded KoboldAI Lite web UI
and resources. The upstream PyInstaller blob and the bundled prebuilt glslc are
not used (Vulkan shaders build with the system media-libs/shaderc), and no
model weights are shipped.

USE=vulkan is upstream's official GPU path for both AMD and NVIDIA, and is
build-verified here (CPU + Vulkan). CUDA and ROCm are intentionally omitted for
now: CUDA cannot be verified on this host, and koboldcpp's ROCm support is an
unofficial upstream fork whose Makefile GPU_TARGETS handling needs work. Both
are follow-ups.