AUR (en) - llama-hdd

Search Criteria

Enter search criteria

Search by

Keywords

Out of Date

Sort by

Sort order

Per page

Git Clone URL:	https://aur.archlinux.org/llama-hdd.git (read-only, click to copy)
Package Base:	llama-hdd
Description:	LLM inference in C/C++ with disk-backed prompt-checkpoint persistence (llama.cpp soft-fork)
Upstream URL:	https://codeberg.org/LuminaNAO/llama-hdd.cpp
Licenses:	MIT
Conflicts:	llama.cpp, llama.cpp-cuda, llama.cpp-hip, llama.cpp-vulkan
Provides:	llama.cpp
Submitter:	LuminaNAO
Maintainer:	LuminaNAO
Last Packager:	LuminaNAO
Votes:	0
Popularity:	0.000000
First Submitted:	2026-06-01 14:32 (UTC)
Last Updated:	2026-07-11 05:36 (UTC)

curl (curl-git^AUR, curl-c-ares^AUR)
gcc-libs (gcc-libs-git^AUR, gcc-libs-fast-optimized^AUR, gccrs-libs-git^AUR, gcc-libs-snapshot^AUR)
glibc (glibc-git^AUR, glibc-git-native-pgo^AUR, glibc-eac^AUR)
openmp
cmake (cmake3^AUR, cmake-git^AUR) (make)
git (git-git^AUR, git-gl^AUR, git-wd40^AUR) (make)
python (make)
cuda (cuda11.1^AUR, cuda-12.2^AUR, cuda12.0^AUR, cuda11.4^AUR, cuda-12.5^AUR, cuda-12.8^AUR, cuda-pascal^AUR, cuda-12.9^AUR) (optional) – NVIDIA GPU acceleration (build with LLAMA_HDD_BACKEND=cuda)
llama-launcher^AUR (optional) – launcher with --hdd-cache mode that drives this fork's sidecar feature
rocm-hip-sdk (opencl-amd-dev^AUR, rocm-nightly-gfx110x-bin^AUR, rocm-nightly-gfx1151-bin^AUR, rocm-nightly-gfx120x-all-bin^AUR) (optional) – AMD GPU acceleration (build with LLAMA_HDD_BACKEND=rocm)
vulkan-icd-loader (vulkan-icd-loader-git^AUR) (optional) – Vulkan GPU acceleration (build with LLAMA_HDD_BACKEND=vulkan)