Package Details: llama.cpp-cuda b10092-1

Git Clone URL: https://aur.archlinux.org/llama.cpp-cuda.git (read-only, click to copy)
Package Base: llama.cpp-cuda
Description: Port of Facebook's LLaMA model in C/C++ (with NVIDIA CUDA optimizations)
Upstream URL: https://github.com/ggml-org/llama.cpp
Licenses: MIT
Conflicts: ggml, libggml, llama.cpp
Provides: llama.cpp
Submitter: txtsd
Maintainer: fabse
Last Packager: fabse
Votes: 22
Popularity: 2.97
First Submitted: 2024-10-26 20:17 (UTC)
Last Updated: 2026-07-23 06:32 (UTC)

Dependencies (19)

Required by (13)

Sources (3)

Pinned Comments

txtsd commented on 2024-10-26 20:17 (UTC) (edited on 2024-12-06 14:15 (UTC) by txtsd)

Alternate versions

llama.cpp
llama.cpp-vulkan
llama.cpp-sycl-fp16
llama.cpp-sycl-fp32
llama.cpp-cuda
llama.cpp-cuda-f16
llama.cpp-hip

Latest Comments

« First ‹ Previous 1 2 3 4 5 6 7 8 9 .. 11 Next › Last »

ilovesusu commented on 2026-03-26 04:20 (UTC)

Why isn't this package being updated anymore?

bionade24 commented on 2026-03-16 09:16 (UTC) (edited on 2026-03-16 09:18 (UTC) by bionade24)

@envolution: Why is this pkg not being updated anymore? There are multiple people down in the comments whose updated PKGBUILD you just have to verify & copy over.

@pussyhut: Please be transparent & update your comment when your request has been rejected.

JamesMowery commented on 2026-02-11 14:53 (UTC)

Thank you for helping to keep this updated! :)

pussyhut commented on 2026-02-11 12:09 (UTC)

Hello everyone, I have sent a request to take over the maintenance of llama.cpp-cuda, and the pkgbuild will be hosted here: https://github.com/KFERMercer/pkgbuild-llama.cpp-cuda

Spilver commented on 2026-01-26 18:28 (UTC) (edited on 2026-01-26 18:33 (UTC) by Spilver)

If you have error: Compiling the CUDA compiler identification source file "CMakeCUDACompilerId.cu" failed.
Modify PKGBUILD, add: -DCMAKE_C_COMPILER=gcc-12 -DCMAKE_CXX_COMPILER=g++-12
You need to install g++-12 and gcc-12, and apply 2 patches to your cuda-12 installation headers after:
First patch
Second patch

pussyhut commented on 2026-01-26 01:26 (UTC)

@envolution is missing since 2025-12-11... As for OOD, the direct cause is https://github.com/envolution/aur/pull/22

angryonline commented on 2026-01-17 21:02 (UTC)

Why is this no longer being updated

envolution commented on 2025-10-02 08:12 (UTC)

@sserhi you may want to manage that in your /etc/makepkg.conf - MAKEFLAGS

sserhii commented on 2025-10-01 23:45 (UTC) (edited on 2025-10-01 23:46 (UTC) by sserhii)

Hey,

Any chance to parallelize the build like this:

❯ git diff                                              
diff --git a/PKGBUILD b/PKGBUILD
index 0a18397..056a382 100644
--- a/PKGBUILD
+++ b/PKGBUILD
@@ -96,7 +96,7 @@ build() {
     _cmake_options+=(${aur_llamacpp_cmakeopts})
   fi
   cmake "${_cmake_options[@]}"
-  cmake --build build
+  cmake --build build -j"$(nproc)"
 }

It provides a noticeable speed up, at least for me: the build process takes about 2.5 minutes with the patch applied vs about 15 minutes without.

Thanks!

« First ‹ Previous 1 2 3 4 5 6 7 8 9 .. 11 Next › Last »