| 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: | 1 |
| Popularity: | 0.58 |
| First Submitted: | 2024-10-26 18:11 (UTC) |
| Last Updated: | 2024-11-22 11:24 (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
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 It's been outdated for a long time now.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.
I have the same problem with 'syclcompat/math.hpp' file not found .
The latest intel-oneapi-basekit-2024.1.0.596-3 is installed.
@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 I'm trying to figure out if it's an upstream issue or if it's because of the outdated intel-oneapi-basekit package.
I'm getting an error
/home/pepijn/aur/llama.cpp-sycl-f16/src/llama.cpp/ggml/src/ggml-sycl/../ggml-sycl/dpct/helper.hpp:18:10: fatal error: 'syclcompat/math.hpp' file not found
18 | #include <syclcompat/math.hpp>
| ^~~~~~~~~~~~~~~~~~~~~
Pinned Comments
txtsd commented on 2024-10-26 20:15 (UTC)
Alternate versions
llama.cpp
llama.cpp-vulkan
llama.cpp-sycl-fp16
llama.cpp-sycl-fp32
llama.cpp-opencl
llama.cpp-cuda
llama.cpp-hip