Package Details: llama.cpp-sycl-f16 b4823-1

Git Clone URL: https://aur.archlinux.org/llama.cpp-sycl-f16.git (read-only, click to copy)
Package Base: llama.cpp-sycl-f16
Description: Port of Facebook's LLaMA model in C/C++ (with Intel SYCL GPU optimizations and F16)
Upstream URL: https://github.com/ggerganov/llama.cpp
Licenses: MIT
Conflicts: llama.cpp
Provides: llama.cpp
Submitter: txtsd
Maintainer: txtsd
Last Packager: txtsd
Votes: 2
Popularity: 1.05
First Submitted: 2024-10-26 18:11 (UTC)
Last Updated: 2025-03-04 18:16 (UTC)

Pinned Comments

txtsd commented on 2024-10-26 20:15 (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 Next › Last »

bionade24 commented on 2025-02-11 14:41 (UTC)

Still broken: Current build log at https://abs-cd.oscloud.info/cd_manager/llama.cpp-sycl-f16

You get past the SYCL_EXTERNAL issue by providing a makepkg.conf without most of the -fsomething C(XX)FLAGS, but run into architecture problems afterwards.

bionade24 commented on 2025-02-06 21:51 (UTC) (edited on 2025-02-08 10:48 (UTC) by bionade24)

intel-compute-runtime should be an optdepend of this and the -f32 pkg. It's needed for OneAPI GPU access.

@greyltc I could neither build it (with intel-oneapi-basekit-2025) in a clean buildenv, with a custom makepkg.conf that removes all the C(XX)FLAGS nor manually. I got past the undefined function without SYCL_EXTERNAL with the latter 2, but the got a shitton of errors related to typedefs where my first guess is that the compiler should have used stdlib headers under /opt/intel/oneapi. Currently trying to build in docker.

Edit: Docker builds & runs, but I didn't have any luck building it on Arch. I also tried changing the BLAS libary to OpenBLAS, setting -march=haswell to maybe get those weird intrinsincs errors away, but to no help.

greyltc commented on 2024-12-21 17:19 (UTC)

I'm not sure the SYCL_EXTERNAL issue is upstream's problem. I think it might be caused by the environment variables that makepkg sets when it builds packages. Still trying to figure it out...

txtsd commented on 2024-12-21 07:42 (UTC)

Thanks @grelytc! Could you post an upstream issue about SYCL_EXTERNAL?

greyltc commented on 2024-12-18 18:44 (UTC)

@txtsd, you can depend on https://aur.archlinux.org/packages/intel-oneapi-basekit-2025 here if you want the latest intel-oneapi-basekit. That solves the "'syclcompat/math.hpp' file not found" issue, but even with that solved the package still won't build.

ioctl commented on 2024-11-30 18:21 (UTC)

While this package cannot be build one may use Intel's ipex-llm project, that compatible with llama.cpp and works very fast with Archlinux intel-oneapi-basekit 2024.1.

Here is official guide: https://github.com/intel-analytics/ipex-llm/blob/main/docs/mddocs/Quickstart/llama_cpp_quickstart.md

pepijndevos commented on 2024-11-22 07:32 (UTC)

I was told they wont update it until after the Python 3.13 migration.

I have updated it locally and am now getting

/usr/lib64/gcc/x86_64-pc-linux-gnu/14.2.1/../../../../include/c++/14.2.1/array:217:2: error: SYCL kernel cannot call an undefined function without SYCL_EXTERNAL attribute

txtsd commented on 2024-11-22 06:44 (UTC)

It's the intel-oneapi-basekit package. It's been outdated for a long time now. I'll send a patch and see if they'll accept it.

ioctl commented on 2024-11-22 06:37 (UTC)

I have the same problem with 'syclcompat/math.hpp' file not found .

The latest intel-oneapi-basekit-2024.1.0.596-3 is installed.

txtsd commented on 2024-11-22 05:34 (UTC)

@pepijndevos Thanks for reporting! I'm trying to figure out if it's an upstream issue or if it's because of the outdated intel-oneapi-basekit package.

1 2 Next › Last »