AUR (en) - ollama-cuda-git

Search Criteria

Package Details: ollama-cuda-git 0.5.4+r3750+gdd352ab27-2

Git Clone URL:	https://aur.archlinux.org/ollama-cuda-git.git (read-only, click to copy)
Package Base:	ollama-cuda-git
Description:	Create, run and share large language models (LLMs)
Upstream URL:	https://github.com/ollama/ollama
Licenses:	MIT
Conflicts:	ollama
Provides:	ollama
Submitter:	sr.team
Maintainer:	envolution
Last Packager:	envolution
Votes:	5
Popularity:	1.63
First Submitted:	2024-02-22 23:22 (UTC)
Last Updated:	2024-12-22 15:01 (UTC)

Git Clone URL:

https://aur.archlinux.org/ollama-cuda-git.git (read-only, click to copy)

Package Base:

ollama-cuda-git

Description:

Create, run and share large language models (LLMs)

Upstream URL:

https://github.com/ollama/ollama

Licenses:

MIT

Conflicts:

ollama

Provides:

ollama

Submitter:

sr.team

Maintainer:

envolution

Last Packager:

envolution

Votes:

Popularity:

1.63

First Submitted:

2024-02-22 23:22 (UTC)

Last Updated:

2024-12-22 15:01 (UTC)

Dependencies (4)

cmake (cmake-git^AUR) (make)
cuda (cuda11.1^AUR, cuda-12.2^AUR, cuda12.0^AUR, cuda11.4^AUR, cuda11.4-versioned^AUR, cuda12.0-versioned^AUR) (make)
git (git-git^AUR, git-gl^AUR) (make)
go (go-git^AUR, gcc-go-git^AUR, gcc-go-snapshot^AUR, gcc-go) (make)

Required by (26)

ai-writer (requires ollama)
alpaca-ai (requires ollama)
alpaca-git (requires ollama) (optional)
alpaka-git (requires ollama)
anythingllm-desktop-bin (requires ollama)
chatd (requires ollama)
chatd-bin (requires ollama)
gollama (requires ollama) (optional)
gollama-git (requires ollama) (optional)
hoarder (requires ollama) (optional)
hollama-bin (requires ollama)
litellm (requires ollama) (optional)
litellm-ollama (requires ollama)
llocal-bin (requires ollama)
lobe-chat (requires ollama) (optional)
lumen (requires ollama) (optional)
maestro (requires ollama) (optional)
maestro-git (requires ollama) (optional)
ollamamodelupdater (requires ollama) (optional)
ollamamodelupdater-bin (requires ollama) (optional)
open-webui (requires ollama) (optional)
python-ollama (requires ollama)
python-ollama-git (requires ollama)
screenshot_llm (requires ollama) (optional)
screenshot_llm-git (requires ollama) (optional)
tlm (requires ollama) (optional)

Sources (5)

Yes it is fixed and build and run.thanks.

sr.team commented on 2024-04-01 12:43 (UTC)

@nmanarch thanks for report. This problem must be fixed now

nmanarch commented on 2024-03-31 23:00 (UTC) (edited on 2024-03-31 23:59 (UTC) by nmanarch)

Hi ! the build failed..? someone have some tricks to solve ?


/var/tmp/pamac-build-nico/ollama-cuda-git/src/ollama/llm/llama.cpp/ggml-cuda.cu:9432:13: note: in instantiation of function template specialization 'mul_mat_vec_q_cuda<256, 8, block_iq3_s, 1, &vec_dot_iq3_s_q8_1>' requested here
            mul_mat_vec_q_cuda<QK_K, QI3_XS, block_iq3_s, 1, vec_dot_iq3_s_q8_1>
            ^
error: option 'cf-protection=return' cannot be specified on this target
error: option 'cf-protection=branch' cannot be specified on this target
194 warnings and 2 errors generated when compiling for gfx1010.
make[3]: *** [CMakeFiles/ggml.dir/build.make:132: CMakeFiles/ggml.dir/ggml-cuda.cu.o] Error 1
make[2]: *** [CMakeFiles/Makefile2:838: CMakeFiles/ggml.dir/all] Error 2
make[1]: *** [CMakeFiles/Makefile2:3575: ext_server/CMakeFiles/ext_server.dir/rule] Error 2
make: *** [Makefile:1440: ext_server] Error 2
llm/generate/generate_linux.go:3: running "bash": exit status 2
==> ERREUR : Une erreur s’est produite dans build().
    Abandon…

So i have found on : https://aur.archlinux.org/packages/ollama-rocm-git?O=10 So i remove my fcf-protection in my /etc/makepkg.conf .

But now i have


 g++ -fPIC -g -shared -o ../llama.cpp/build/linux/x86_64/rocm/lib/libext_server.so -Wl,--whole-archive ../llama.cpp/build/linux/x86_64/rocm/ext_server/libext_server.a -Wl,--no-whole-archive ../llama.cpp/build/linux/x86_64/rocm/common/libcommon.a ../llama.cpp/build/linux/x86_64/rocm/libllama.a '-Wl,-rpath,$ORIGIN' -lpthread -ldl -lm -L/opt/rocm/lib -L/opt/amdgpu/lib/x86_64-linux-gnu/ '-Wl,-rpath,$ORIGIN/../../rocm/' -lhipblas -lrocblas -lamdhip64 -lrocsolver -lamd_comgr -lhsa-runtime64 -lrocsparse -ldrm -ldrm_amdgpu
/usr/sbin/ld : ../llama.cpp/build/linux/x86_64/rocm/ext_server/libext_server.a : membre %B dans l'archive n'est pas un objet
collect2: erreur: ld a retourné le statut de sortie 1
llm/generate/generate_linux.go:3: running "bash": exit status 1
==> ERREUR : Une erreur s’est produite dans build().
    Abandon…

Arch Linux User Repository