Package Details: llama.cpp-cuda b6129-1

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/ggerganov/llama.cpp
Licenses: MIT
Conflicts: ggml, libggml, llama.cpp
Provides: llama.cpp
Submitter: txtsd
Maintainer: envolution
Last Packager: envolution
Votes: 8
Popularity: 0.83
First Submitted: 2024-10-26 20:17 (UTC)
Last Updated: 2025-08-11 13:25 (UTC)

Required by (0)

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

1 2 3 4 Next › Last »

envolution commented on 2025-08-01 21:46 (UTC)

@AlxQ should be okay now - thanks for the report

envolution commented on 2025-08-01 19:48 (UTC)

@AlxQ it's picking up the commit from the aur repo somehow - I can have a look into this later today.

.git/logs/refs/remotes/origin/HEAD:0000000000000000000000000000000000000000 9ca426da1fdf involution involution@gmail.com 1754071863 -0400 clone: from ssh://aur.archlinux.org/llama.cpp-cuda.git

It's definitely the right upstream code - just not properly reflected in the version strings

AlxQ commented on 2025-08-01 16:30 (UTC)

The current PKGBUILD builds only b982-9ca426d build

$ llama-server --version
ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 CUDA devices:
  Device 0: NVIDIA GeForce RTX 4060 Ti, compute capability 8.9, VMM: yes
version: 982 (9ca426d)
built with cc (GCC) 15.1.1 20250729 for x86_64-pc-linux-gnu

marceldev89 commented on 2025-08-01 10:14 (UTC)

The current PKGBUILD no longer compiles a native build due to makepkg providing the SOURCE_DATE_EPOCH environment variable. This variable is checked in ggml/CMakeLists.txt:

if (CMAKE_CROSSCOMPILING OR DEFINED ENV{SOURCE_DATE_EPOCH})
    message(STATUS "Setting GGML_NATIVE_DEFAULT to OFF")
    set(GGML_NATIVE_DEFAULT OFF)
else()
    set(GGML_NATIVE_DEFAULT ON)
endif()

envolution commented on 2025-07-31 16:34 (UTC)

@AlxQ thanks, fixed

AlxQ commented on 2025-07-31 16:26 (UTC)

==> Validating source files with sha256sums...
    llama.cpp-cuda-b6045.tar.gz ... FAILED
    llama.cpp.conf ... Passed
    llama.cpp.service ... Passed
==> ERROR: One or more files did not pass the validity check!
 -> error making: llama.cpp-cuda-exit status 1
 -> Failed to install the following packages. Manual intervention is required:
llama.cpp-cuda - exit status 1

trougnouf commented on 2025-07-31 11:07 (UTC) (edited on 2025-07-31 16:10 (UTC) by trougnouf)

I've had cuda installed long before the last reboot, idk what's the issue then.

edit: it seems to be because I used the fish shell. Building from bash works.

edit: unrelated but I found llama.cpp-vulkan to be 2-4 x faster.

envolution commented on 2025-07-31 05:46 (UTC)

just a couple of minor changes in the build

python modules are now identified as optional for the conversion script
changed from git to tar.gz due to the git repo initial sync being so large

@trougnouf you need to source /etc/profile or log out and back in after installing cuda

trougnouf commented on 2025-07-30 20:01 (UTC)

I can get through that error with -DCMAKE_CUDA_COMPILER=/opt/cuda/bin/nvcc but then I get several more during the compilation.

trougnouf commented on 2025-07-30 19:42 (UTC)

I get the following error:

-- Could not find nvcc, please set CUDAToolkit_ROOT.
CMake Error at ggml/src/ggml-cuda/CMakeLists.txt:183 (message):
  CUDA Toolkit not found