gpo.zugaina.org

Search Portage & Overlays:

sci-misc/llama-cpp

Port of Facebook's LLaMA model in C/C++

Screenshots

  • llama-cpp-9999
    curl openblas +openmp blis hip cuda opencl vulkan flexiblas +amdgpu_targets_gfx908 +amdgpu_targets_gfx90a +amdgpu_targets_gfx942 +amdgpu_targets_gfx1030 +amdgpu_targets_gfx1100 +amdgpu_targets_gfx1101 +amdgpu_targets_gfx1200 +amdgpu_targets_gfx1201 amdgpu_targets_gfx803 amdgpu_targets_gfx900 amdgpu_targets_gfx906 amdgpu_targets_gfx940 amdgpu_targets_gfx941 amdgpu_targets_gfx1010 amdgpu_targets_gfx1011 amdgpu_targets_gfx1012 amdgpu_targets_gfx1031 amdgpu_targets_gfx1102 amdgpu_targets_gfx1103 amdgpu_targets_gfx1150 amdgpu_targets_gfx1151

    View      Download      Browse     License: MIT   
    Overlay: guru
  • llama-cpp-9999
    ~amd64
    curl openblas +openmp blis hip cuda opencl vulkan +amdgpu_targets_gfx908 +amdgpu_targets_gfx90a +amdgpu_targets_gfx942 +amdgpu_targets_gfx1030 +amdgpu_targets_gfx1100 amdgpu_targets_gfx803 amdgpu_targets_gfx900 amdgpu_targets_gfx906 amdgpu_targets_gfx940 amdgpu_targets_gfx941 amdgpu_targets_gfx1010 amdgpu_targets_gfx1011 amdgpu_targets_gfx1012 amdgpu_targets_gfx1031 amdgpu_targets_gfx1101 amdgpu_targets_gfx1102 amdgpu_targets_gfx1200 amdgpu_targets_gfx1201

    View      Download      Browse     License: MIT   
    Overlay: FireBurn
  • llama-cpp-0_pre6980
    ~amd64
    curl openblas +openmp blis hip cuda opencl vulkan flexiblas +amdgpu_targets_gfx908 +amdgpu_targets_gfx90a +amdgpu_targets_gfx942 +amdgpu_targets_gfx1030 +amdgpu_targets_gfx1100 +amdgpu_targets_gfx1101 +amdgpu_targets_gfx1200 +amdgpu_targets_gfx1201 amdgpu_targets_gfx803 amdgpu_targets_gfx900 amdgpu_targets_gfx906 amdgpu_targets_gfx940 amdgpu_targets_gfx941 amdgpu_targets_gfx1010 amdgpu_targets_gfx1011 amdgpu_targets_gfx1012 amdgpu_targets_gfx1031 amdgpu_targets_gfx1102 amdgpu_targets_gfx1103 amdgpu_targets_gfx1150 amdgpu_targets_gfx1151

    View      Download      Browse     License: MIT   
    Overlay: guru
  • llama-cpp-0_pre6710
    ~amd64
    curl openblas +openmp blis hip cuda opencl vulkan +amdgpu_targets_gfx908 +amdgpu_targets_gfx90a +amdgpu_targets_gfx942 +amdgpu_targets_gfx1030 +amdgpu_targets_gfx1100 +amdgpu_targets_gfx1101 +amdgpu_targets_gfx1200 +amdgpu_targets_gfx1201 amdgpu_targets_gfx803 amdgpu_targets_gfx900 amdgpu_targets_gfx906 amdgpu_targets_gfx940 amdgpu_targets_gfx941 amdgpu_targets_gfx1010 amdgpu_targets_gfx1011 amdgpu_targets_gfx1012 amdgpu_targets_gfx1031 amdgpu_targets_gfx1102 amdgpu_targets_gfx1103 amdgpu_targets_gfx1150 amdgpu_targets_gfx1151

    View      Download      Browse     License: MIT   
    Overlay: guru
  • llama-cpp-0_pre6318
    ~amd64
    curl openblas +openmp blis hip cuda opencl vulkan +amdgpu_targets_gfx908 +amdgpu_targets_gfx90a +amdgpu_targets_gfx942 +amdgpu_targets_gfx1030 +amdgpu_targets_gfx1100 +amdgpu_targets_gfx1101 +amdgpu_targets_gfx1200 +amdgpu_targets_gfx1201 amdgpu_targets_gfx803 amdgpu_targets_gfx900 amdgpu_targets_gfx906 amdgpu_targets_gfx940 amdgpu_targets_gfx941 amdgpu_targets_gfx1010 amdgpu_targets_gfx1011 amdgpu_targets_gfx1012 amdgpu_targets_gfx1031 amdgpu_targets_gfx1102 amdgpu_targets_gfx1103 amdgpu_targets_gfx1150 amdgpu_targets_gfx1151

    View      Download      Browse     License: MIT   
    Overlay: guru
  • llama-cpp-0_pre6140
    ~amd64
    curl openblas +openmp blis hip cuda opencl vulkan +amdgpu_targets_gfx908 +amdgpu_targets_gfx90a +amdgpu_targets_gfx942 +amdgpu_targets_gfx1030 +amdgpu_targets_gfx1100 amdgpu_targets_gfx803 amdgpu_targets_gfx900 amdgpu_targets_gfx906 amdgpu_targets_gfx940 amdgpu_targets_gfx941 amdgpu_targets_gfx1010 amdgpu_targets_gfx1011 amdgpu_targets_gfx1012 amdgpu_targets_gfx1031 amdgpu_targets_gfx1101 amdgpu_targets_gfx1102 amdgpu_targets_gfx1200 amdgpu_targets_gfx1201

    View      Download      Browse     License: MIT   
    Overlay: guru
  • llama-cpp-0_pre5633-r1
    ~amd64
    curl openblas blis hip cuda +amdgpu_targets_gfx908 +amdgpu_targets_gfx90a +amdgpu_targets_gfx942 +amdgpu_targets_gfx1030 +amdgpu_targets_gfx1100 amdgpu_targets_gfx803 amdgpu_targets_gfx900 amdgpu_targets_gfx906 amdgpu_targets_gfx940 amdgpu_targets_gfx941 amdgpu_targets_gfx1010 amdgpu_targets_gfx1011 amdgpu_targets_gfx1012 amdgpu_targets_gfx1031 amdgpu_targets_gfx1101 amdgpu_targets_gfx1102 amdgpu_targets_gfx1200 amdgpu_targets_gfx1201

    View      Download      Browse     License: MIT   
    Overlay: guru
  • llama-cpp-0_pre5332
    ~amd64
    curl openblas blis hip +amdgpu_targets_gfx906 +amdgpu_targets_gfx908 +amdgpu_targets_gfx90a +amdgpu_targets_gfx942 +amdgpu_targets_gfx1030 +amdgpu_targets_gfx1100 amdgpu_targets_gfx803 amdgpu_targets_gfx900 amdgpu_targets_gfx940 amdgpu_targets_gfx941 amdgpu_targets_gfx1010 amdgpu_targets_gfx1011 amdgpu_targets_gfx1012 amdgpu_targets_gfx1031 amdgpu_targets_gfx1101 amdgpu_targets_gfx1102

    View      Download      Browse     License: MIT   
    Overlay: guru

ChangeLog

commit b2cf10b4087169fd6ec3bf907138c938a282248e
Author: Sergey Alirzaev <l29ah@riseup.net>
Date: Mon Nov 10 03:24:29 2025 +0100

sci-misc/llama-cpp: + flexiblas backend

Signed-off-by: Sergey Alirzaev <l29ah@riseup.net>

commit 8e54fa1530473f335c80c9707a9036029cb19984
Author: Sergey Alirzaev <l29ah@riseup.net>
Date: Sat Nov 8 04:10:41 2025 +0100

sci-misc/llama-cpp: drop 0_pre4576

Signed-off-by: Sergey Alirzaev <l29ah@riseup.net>

commit 4eab3d67999ffbee19a71a22ad7d01c1259125f4
Author: Sergey Alirzaev <l29ah@riseup.net>
Date: Sat Nov 8 04:10:20 2025 +0100

sci-misc/llama-cpp: add 0_pre6980

Signed-off-by: Sergey Alirzaev <l29ah@riseup.net>

commit 0d5b89bb35c22be5c5861ddc97fba7de6b7663ac
Author: Sergey Alirzaev <l29ah@riseup.net>
Date: Sat Nov 8 03:40:54 2025 +0100

sci-misc/llama-cpp: fixup bdep

Signed-off-by: Sergey Alirzaev <l29ah@riseup.net>

commit acfe4100ae65b6aeff208b50529bd8b132ded8f3
Author: Sergey Alirzaev <l29ah@riseup.net>
Date: Wed Oct 8 04:10:18 2025 +0200

sci-misc/llama-cpp: bump up to 6710, rm old

LFM2-MoE support and fixes

Signed-off-by: Sergey Alirzaev <l29ah@riseup.net>

commit 8e62615b17434f76bac0392acc51942f41b0ebe9
Author: Sergey Alirzaev <l29ah@riseup.net>
Date: Fri Sep 12 02:40:18 2025 +0200

sci-misc/llama-cpp: depend on shaderc for glslc

Closes: https://bugs.gentoo.org/962755
Signed-off-by: Sergey Alirzaev <l29ah@riseup.net>

commit 894d171ba3a079365d5e2a73de290cf14cd71595
Author: Sergey Alirzaev <l29ah@riseup.net>
Date: Fri Aug 29 18:25:30 2025 +0200

sci-misc/llama-cpp: add 0_pre6318, drop 0_pre6092

lots of bugfixes and new model architectures

Signed-off-by: Sergey Alirzaev <l29ah@riseup.net>

commit a16045671d92d0f8e5b9949eadd44af61e9653e1
Author: Sergey Alirzaev <l29ah@riseup.net>
Date: Tue Aug 12 23:38:33 2025 +0200

sci-misc/llama-cpp: add 0_pre6140, drop 0_pre6002

for gpt-oss support

Signed-off-by: Sergey Alirzaev <l29ah@riseup.net>

commit 3733474f9c1d366432ae59570970b06833cebb5e
Author: Sergey Alirzaev <l29ah@riseup.net>
Date: Sun Aug 10 02:35:22 2025 +0200

sci-misc/llama-cpp: handle automagic openmp dep

enabled by default as otherwise results in severe performance hit
see https://github.com/ggml-org/llama.cpp/issues/12171

Signed-off-by: Sergey Alirzaev <l29ah@riseup.net>

commit d34ca91c8f27f4b06f5ea95f165a680c87172f19
Author: Sergey Alirzaev <l29ah@riseup.net>
Date: Tue Aug 5 22:25:44 2025 +0200

sci-misc/llama-cpp: add 0_pre6092, drop 0_pre5857

for glm4moe support

Signed-off-by: Sergey Alirzaev <l29ah@riseup.net>

commit dd6553618adb7bb29489c08843bac9618b42ee27
Author: Sergey Alirzaev <l29ah@riseup.net>
Date: Thu Jul 31 17:03:55 2025 +0200

sci-misc/llama-cpp: describe opencl USE

Signed-off-by: Sergey Alirzaev <l29ah@riseup.net>

commit bf6fdb43eb7155c0ca1e4b40f2d0e0a4a0732adf
Author: Sergey Alirzaev <l29ah@riseup.net>
Date: Mon Jul 28 00:59:07 2025 +0200

sci-misc/llama-cpp: + opencl backend, bump

Signed-off-by: Sergey Alirzaev <l29ah@riseup.net>

commit 9531e4e2766665251f392baac69c3e752439c265
Author: David Roman <davidroman96@gmail.com>
Date: Thu Jul 24 01:35:43 2025 +0200

Revert "sci-misc/llama-cpp: keyword 0_pre5857 for ~ppc64"

This reverts commit cec394f5db5e12b2b2da45109f52d0f3a2a68d15.
Signed-off-by: David Roman <davidroman96@gmail.com>

commit cec394f5db5e12b2b2da45109f52d0f3a2a68d15
Author: Piotr Kubaj <pkubaj@anongoth.pl>
Date: Wed Jul 23 14:48:45 2025 +0200

sci-misc/llama-cpp: keyword 0_pre5857 for ~ppc64

Signed-off-by: Piotr Kubaj <pkubaj@anongoth.pl>

commit 451623c534e7e4fa47a2793c85f5f4fbabc518c6
Author: Paul Zander <negril.nx+gentoo@gmail.com>
Date: Tue Jul 22 19:55:49 2025 +0200

sci-misc/llama-cpp: set CUDAHOSTCXX via cuda.eclass

Closes: https://bugs.gentoo.org/960549
Signed-off-by: Paul Zander <negril.nx+gentoo@gmail.com>

commit bd53f5db4fd7a23956623e81ce0058505609928b
Author: Sergey Alirzaev <l29ah@riseup.net>
Date: Thu Jul 10 02:16:05 2025 +0200

sci-misc/llama-cpp: fix hip/rocm, remove old

Signed-off-by: Sergey Alirzaev <l29ah@riseup.net>

commit 1ac2399f369cbb94c1e3fd9e94e4bbbb4da0f8ce
Author: Sergey Alirzaev <l29ah@riseup.net>
Date: Fri Jul 4 04:17:10 2025 +0200

sci-misc/llama-cpp: sync live

Signed-off-by: Sergey Alirzaev <l29ah@riseup.net>

commit 37f4b2ddc87bc6d56eea5298374186838a39f1b4
Author: Sergey Alirzaev <l29ah@riseup.net>
Date: Fri Jul 4 00:22:34 2025 +0200

sci-misc/llama-cpp: vulkan support

Signed-off-by: Sergey Alirzaev <l29ah@riseup.net>

commit 36a39a0a8040d36ff378936b335447b7d9f315a7
Author: Sergey Alirzaev <l29ah@riseup.net>
Date: Thu Jul 3 21:32:59 2025 +0200

sci-misc/llama-cpp: avoid clashing with whisper.cpp

Signed-off-by: Sergey Alirzaev <l29ah@riseup.net>

commit d233181e96f30991c95ac43d5c70c8a4df145b3b
Author: Alexey Korepanov <kaikaikai@yandex.ru>
Date: Mon Jun 16 21:01:09 2025 +0800

sci-misc/llama-cpp: support cuda, update upstream url

Signed-off-by: Alexey Korepanov <kaikaikai@yandex.ru>

commit 9343efb98748669fe5078b18c349fc28bd778ef2
Author: Sergey Alirzaev <l29ah@riseup.net>
Date: Wed Jun 11 14:52:57 2025 +0200

sci-misc/llama-cpp: add 0_pre5633, drop 0_pre4763

Signed-off-by: Sergey Alirzaev <l29ah@riseup.net>

commit 1b3ace659df434818b1aeeda7f2f70f3e07f9ea9
Author: Sergey Alirzaev <l29ah@riseup.net>
Date: Sat May 17 14:57:10 2025 +0200

sci-misc/llama-cpp: enable rpc

Signed-off-by: Sergey Alirzaev <l29ah@riseup.net>

commit ea094d31a2643de0fec13f7f25b5870d40b8f4e9
Author: Sergey Alirzaev <l29ah@riseup.net>
Date: Sat May 10 01:38:54 2025 +0200

sci-misc/llama-cpp: add 0_pre5332

Signed-off-by: Sergey Alirzaev <l29ah@riseup.net>

commit edf82b33406c122f0cc42d8d7773c68e67fd986d
Author: Sergey Alirzaev <l29ah@riseup.net>
Date: Thu Apr 10 21:52:02 2025 +0200

sci-misc/llama-cpp: add 0_pre5097

Signed-off-by: Sergey Alirzaev <l29ah@riseup.net>

commit 19e74ee6a141256e081b6f4d7749ece9af97b307
Author: Sergey Alirzaev <l29ah@riseup.net>
Date: Fri Mar 7 12:16:01 2025 +0100

sci-misc/llama-cpp: add 0_pre4848

for QwQ-32B --jinja support

Signed-off-by: Sergey Alirzaev <l29ah@riseup.net>

commit dba4c2b3be4988d53c662f849e3785bf45488ddf
Author: Sergey Alirzaev <l29ah@riseup.net>
Date: Sun Feb 23 18:54:20 2025 +0100

sci-misc/llama-cpp: add 0_pre4763

Signed-off-by: Sergey Alirzaev <l29ah@riseup.net>

commit e01288b79918003e5e4a26936c4ce46aa746e5b3
Author: Sergey Alirzaev <l29ah@riseup.net>
Date: Thu Feb 20 15:57:54 2025 +0100

sci-misc/llama-cpp: Add ROCm 6.3 HIP support

Closes: https://bugs.gentoo.org/949856
Signed-off-by: Sergey Alirzaev <l29ah@riseup.net>

commit a48cf7afbbf35240bfe3cf0736098a8f7ec66c92
Author: Alexey Korepanov <kaikaikai@yandex.ru>
Date: Sun Feb 9 11:51:53 2025 +0000

sci-misc/llama-cpp: support OpenBLAS or BLIS backends

A significant speed up in some workflows when running on a CPU

Signed-off-by: Alexey Korepanov <kaikaikai@yandex.ru>

commit fb105c916a2ee882686351f01f149e71594261cf
Author: Alexey Korepanov <kaikaikai@yandex.ru>
Date: Sat Feb 8 16:49:15 2025 +0000

sci-misc/llama-cpp: add dependencies on curl and numpy

Signed-off-by: Alexey Korepanov <kaikaikai@yandex.ru>

commit b228272c6c4d9a2d51f473a6357c7341c1531396
Author: Sergey Alirzaev <l29ah@riseup.net>
Date: Sat Feb 1 12:19:51 2025 +0100

sci-misc/llama-cpp: strip march=native

Closes: https://bugs.gentoo.org/949130
Signed-off-by: Sergey Alirzaev <l29ah@riseup.net>

commit 76de14abfe565eb3b06b1925f1995436f1dc322d
Author: Sergey Alirzaev <l29ah@riseup.net>
Date: Wed Jan 29 01:14:22 2025 +0100

sci-misc/llama-cpp: hopefully satisfy email-checker.py

Signed-off-by: Sergey Alirzaev <l29ah@riseup.net>

commit ab2a79180fb2b2d9bbe7531d0280d7099c773937
Author: Sergey Alirzaev <l29ah@riseup.net>
Date: Wed Jan 29 01:11:11 2025 +0100

sci-misc/llama-cpp: new package, add 0_pre4576, 9999

Signed-off-by: Sergey Alirzaev <l29ah@riseup.net>

commit db9e23974f8408184fce018d6d95643883bb8dab
Author: Takuya Wakazono <pastalian46@gmail.com>
Date: Tue Jan 28 00:06:01 2025 +0900

Revert "sci-misc/llama-cpp: new package, add 0_pre4564, 9999"

This reverts commit e933540939add62cd4de6a464ddf73f912c423e6.

This ebuild has too many issues.
- missing manifest
- use of deprecated eclass
- broken dependency
- undescribed USE flags
- visible keyword for vcs version

Please get advice on a GitHub PR or IRC before committing

Signed-off-by: Takuya Wakazono <pastalian46@gmail.com>

commit e933540939add62cd4de6a464ddf73f912c423e6
Author: Sergey Alirzaev <l29ah@riseup.net>
Date: Mon Jan 27 12:52:32 2025 +0100

sci-misc/llama-cpp: new package, add 0_pre4564, 9999

Signed-off-by: Sergey Alirzaev <l29ah@riseup.net>