Package Details: llama.cpp-cuda b5097-1

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: libggml, llama.cpp
Provides: llama.cpp
Submitter: txtsd
Maintainer: txtsd
Last Packager: txtsd
Votes: 6
Popularity: 0.58
First Submitted: 2024-10-26 20:17 (UTC)
Last Updated: 2025-04-10 02:01 (UTC)

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 Next › Last »

i2z1 commented on 2025-03-02 11:37 (UTC) (edited on 2025-03-02 11:38 (UTC) by i2z1)

Why are you using Kompute, particularly from the fork (https://github.com/nomic-ai/kompute.git - fork insted of mainline https://github.com/KomputeProject/kompute repo), specifically for llama.cpp CUDA version? I think it would be more convenient to create a separate package for the Kompute backend and have llama.cpp-cuda depend only on CUDA-related dependencies? without Kompute backend dependencies.

chiz commented on 2025-02-23 10:23 (UTC) 

llama.cpp-cuda: /usr/lib/libggml-base.so exists in the file system (owned by whisper.cpp-cuda)
llama.cpp-cuda: /usr/lib/libggml-cpu.so exists in the file system (owned by whisper.cpp-cuda)
llama.cpp-cuda: /usr/lib/libggml-cuda.so exists in the file system (owned by whisper.cpp-cuda)
llama.cpp-cuda: /usr/lib/libggml.so exists in the file system (owned by whisper.cpp-cuda)
An error occurred, and no packages were updated.
-> Error during installation: [/home/chi/.cache/yay/llama.cpp-cuda/llama.cpp-cuda-b4762-1-x86_64.pkg.tar.zst] - exit status 1

Sherlock-Holo commented on 2025-02-17 11:26 (UTC)

I recommend include the model template files into the package

https://github.com/ggml-org/llama.cpp/tree/master/models/templates

so we can choose the model template file directly, no need to download these again

<deleted-account> commented on 2025-02-05 09:04 (UTC)

You should export CUDA_PATH and NVCC_CCBIN.
Check /etc/profile.d/cuda.sh

https://wiki.archlinux.org/title/GPGPU#Development_3

hnsl commented on 2025-01-29 20:52 (UTC)

To get this to pass cmake I had to edit the PKGBUILD and add cmake options:

-DCMAKE_CUDA_COMPILER=/opt/cuda/bin/nvcc
-DCMAKE_CUDA_HOST_COMPILER=/usr/bin/gcc-13

I tried pointing it to NVCC via environment variables but it ended up using the wrong GCC version if I did that, which caused compiler errors in CMakeDetermineCompilerId.cmake:865.

ioctl commented on 2025-01-18 19:04 (UTC)

@txtsd, setting CMAKE_CUDA_ARCHITECTURES to my hardware number fixes this problem.

This error appears on the build stage, so it can be reproduced without video card.

txtsd commented on 2024-12-15 15:23 (UTC)

@ioctl Sorry, I don't have the necessary hardware to test. Does not setting CMAKE_CUDA_ARCHITECTURES make it work correctly?

ioctl commented on 2024-12-14 11:17 (UTC)

I have errors running this app on the latest Archlinux on the GeForce RTX 3060 .

The first, there a lot of the following build warning: "nvcc warning : Cannot find valid GPU for '-arch=native', default arch is used"

Then, there are a lot of run errors: "/home/build/.cache/yay/llama.cpp-cuda/src/llama.cpp/ggml/src/ggml-cuda/mmv.cu:51: ERROR: CUDA kernel mul_mat_vec has no device code compatible with CUDA arch 520. ggml-cuda.cu was compiled for: 520"

Setting correct (to my hardware) number instead of "native" in the -DCMAKE_CUDA_ARCHITECTURES cmake option fixes this problem.

txtsd commented on 2024-12-06 13:37 (UTC)

@v1993 I've uploaded llama.cpp-cuda-f16. Please let me know if it works as expected!

1 2 3 Next › Last »