@AlxQ should be okay now - thanks for the report
Search Criteria
Package Details: llama.cpp-cuda b6129-1
Package Actions
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) |
Dependencies (11)
- cuda (cuda11.1AUR, cuda-12.2AUR, cuda12.0AUR, cuda11.4AUR, cuda11.4-versionedAUR, cuda12.0-versionedAUR)
- curl (curl-gitAUR, curl-c-aresAUR)
- gcc-libs (gcc-libs-gitAUR, gccrs-libs-gitAUR, gcc-libs-snapshotAUR)
- glibc (glibc-gitAUR, glibc-linux4AUR, glibc-eacAUR)
- nvidia-utils (nvidia-410xx-utilsAUR, nvidia-440xx-utilsAUR, nvidia-430xx-utilsAUR, nvidia-340xx-utilsAUR, nvidia-470xx-utilsAUR, nvidia-utils-teslaAUR, nvidia-550xx-utilsAUR, nvidia-565xx-utilsAUR, nvidia-525xx-utilsAUR, nvidia-510xx-utilsAUR, nvidia-390xx-utilsAUR, nvidia-vulkan-utilsAUR, nvidia-535xx-utilsAUR, nvidia-utils-betaAUR)
- cmake (cmake3AUR, cmake-gitAUR) (make)
- python-numpy (python-numpy-gitAUR, python-numpy1AUR, python-numpy-mkl-tbbAUR, python-numpy-mklAUR, python-numpy-mkl-binAUR) (optional) – needed for convert_hf_to_gguf.py
- python-pytorch (python-pytorch-cxx11abiAUR, python-pytorch-cxx11abi-optAUR, python-pytorch-cxx11abi-cudaAUR, python-pytorch-cxx11abi-opt-cudaAUR, python-pytorch-cxx11abi-rocmAUR, python-pytorch-cxx11abi-opt-rocmAUR, python-pytorch-cuda, python-pytorch-opt, python-pytorch-opt-cuda, python-pytorch-opt-rocm, python-pytorch-rocm) (optional) – needed for convert_hf_to_gguf.py
- python-safetensorsAUR (python-safetensors-binAUR) (optional) – needed for convert_hf_to_gguf.py
- python-sentencepieceAUR (python-sentencepiece-gitAUR) (optional) – needed for convert_hf_to_gguf.py
- python-transformersAUR (optional) – needed for convert_hf_to_gguf.py
Required by (0)
Sources (3)
envolution commented on 2025-08-01 21:46 (UTC)
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
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