Package Details: llama.cpp-vulkan-git b2698-1

Git Clone URL: https://aur.archlinux.org/llama.cpp-git.git (read-only, click to copy)
Package Base: llama.cpp-git
Description: Port of Facebook's LLaMA model in C/C++ (with Vulkan GPU optimizations)
Upstream URL: https://github.com/ggerganov/llama.cpp
Licenses: MIT
Conflicts: llama.cpp
Provides: llama.cpp
Submitter: robertfoster
Maintainer: robertfoster
Last Packager: robertfoster
Votes: 6
Popularity: 0.96
First Submitted: 2023-03-27 22:24 (UTC)
Last Updated: 2024-04-19 16:24 (UTC)

Latest Comments

« First ‹ Previous 1 2

sr.team commented on 2024-03-24 18:22 (UTC)

The global dependencies requires cuda and hipblas both. Remove it please, and keep only for llama.cpp-cublas-git and llama.cpp-hipblas-git

danisztls commented on 2024-02-07 07:31 (UTC) (edited on 2024-02-07 07:32 (UTC) by danisztls)

Can you add support to compiling with OpenBLAS CMake flags: -DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS on systems with openblas installed?

AndreaCattaneo commented on 2023-09-30 08:12 (UTC) (edited on 2023-09-30 08:13 (UTC) by AndreaCattaneo)

error: failed to commit transaction (conflicting files)

llama.cpp-git: /usr/bin/parallel exists in filesystem (owned by parallel)

chovy commented on 2023-04-23 06:52 (UTC)

does this need to be updated or is it automatic since it uses their git repo?

« First ‹ Previous 1 2