Package Details: beellama.cpp-cuda 0.4.0-1

Git Clone URL: https://aur.archlinux.org/beellama.cpp-cuda.git (read-only, click to copy)
Package Base: beellama.cpp-cuda
Description: DFlash & TurboQuant fork of llama.cpp — up to 3x faster generation and 7.5x more KV cache (CUDA)
Upstream URL: https://github.com/Anbeeld/beellama.cpp
Licenses: MIT
Conflicts: beellama.cpp, beellama.cpp-bin, ggml, libggml, llama.cpp
Provides: beellama.cpp
Submitter: lapsus
Maintainer: lapsus
Last Packager: lapsus
Votes: 0
Popularity: 0.000000
First Submitted: 2026-06-08 11:04 (UTC)
Last Updated: 2026-07-20 13:10 (UTC)

Dependencies (15)

Required by (0)

Sources (3)