Gentoo Portage Overlays - dev-cpp/llama-cpp

dev-cpp/llama-cpp

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

Screenshots

https://github.com/ggerganov/llama.cpp

llama-cpp-9999

~amd64

blas cublas lto tests tools rocm +amdgpu_targets_gfx906 +amdgpu_targets_gfx908 +amdgpu_targets_gfx90a +amdgpu_targets_gfx1030 amdgpu_targets_gfx803 amdgpu_targets_gfx900 amdgpu_targets_gfx1010 amdgpu_targets_gfx1011 amdgpu_targets_gfx1012 amdgpu_targets_gfx1031 amdgpu_targets_gfx1100 amdgpu_targets_gfx1101 amdgpu_targets_gfx1102

View

Download

Browse License: MIT

Overlay: displacer

llama-cpp-0_pre5013

~amd64 ~arm ~arm64 ~arm64-macos ~loong ~riscv ~x64-macos ~x86 ~x86-macos

static lto test examples +server curl hbm android msvc +accelerate blas blis +llamafile cann musa cuda cuda-force-mmq cuda-force-cublas +cuda-unified-memory cuda-f16 cuda-no-peer-copy cuda-no-vmm cuda-fa-all-quants +cuda-graphs hip hip-graphs +hip-no-vmm hip-uma vulkan vulkan-check-results vulkan-debug vulkan-memory-debug vulkan-shader-debug-info vulkan-perf vulkan-validate vulkan-run-tests kompute +openmp rpc opencl opencl-profiling +opencl-embed-kernels +opencl-use-adreno-kernels metal metal-use-bf16 metal-ndebug metal-shader-debug +metal-embed-library +cpu cpu-native cpu_flags_x86_avx cpu_flags_x86_avx_vnni cpu_flags_x86_avx2 cpu_flags_x86_avx512 cpu_flags_x86_avx512_vbmi cpu_flags_x86_avx512_vnni cpu_flags_x86_avx512_bf16 cpu_flags_x86_fma cpu_flags_x86_f16c cpu_flags_x86_amx_tile cpu_flags_x86_amx_int8 cpu_flags_x86_amx_bf16 cpu_flags_x86_sse cpu_flags_x86_sse2 cpu_flags_x86_sse3 cpu_flags_x86_sse4 cpu_flags_x86_sse4a cpu_flags_x86_sse41 cpu_flags_x86_sse42 cpu_flags_x86_ssse3 kleidiai cpu_flags_loong_lasx cpu_flags_loong_lsx cpu_flags_riscv_rvv abi_x86_32 abi_x86_64 abi_x86_x32 abi_mips_n32 abi_mips_n64 abi_mips_o32 abi_s390_32 abi_s390_64 +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: ex_repo

ChangeLog USE Flags Dependencies Reverse Deps Related Bugs

ChangeLog

commit e1ef0714a1a888cc92d9138191131502321d3c90
Author: Arniiiii <lg3dx6fd@gmail.com>
Date: Tue Apr 1 08:44:47 2025 +0000

llama.cpp : update to 5013

commit bb92997974fdfc06af691e7e588e0b30640ae523
Author: Arniiiii <lg3dx6fd@gmail.com>
Date: Sat Mar 1 23:13:21 2025 +0000

fix some RESTRICT="!test? ( test )"

commit e71512fdc867ae4a8489311fb150efd71b25cad1
Author: Arniiiii <lg3dx6fd@gmail.com>
Date: Sat Mar 1 22:31:43 2025 +0000

temporary comment metadata for sycl

commit 2f139bcf9206237c6e394de607bf8bb471cd5ed1
Author: Arniiiii <lg3dx6fd@gmail.com>
Date: Sat Mar 1 22:30:27 2025 +0000

formatting: no `_` in USE flags unless cpu_flags_*

commit 946ae6263441dd909a08802394447c6676767ee0
Author: Arniiiii <lg3dx6fd@gmail.com>
Date: Sat Mar 1 22:04:18 2025 +0000

fix formatting

commit d6273acd19c08dd7a5f3c12db3a6f19cee168f2b
Author: Arniiiii <lg3dx6fd@gmail.com>
Date: Sat Mar 1 20:11:52 2025 +0000

fix some stuff

commit dbd63ccfcc87491ca3768d936c7782b7470c3d97
Author: Arniiiii <lg3dx6fd@gmail.com>
Date: Sat Mar 1 19:52:01 2025 +0000

basic update

commit 176396fb46a5cd4ce5c546b91845235d02916206
Author: Arniiiii <lg3dx6fd@gmail.com>
Date: Fri Feb 28 12:53:46 2025 +0000

temporary update llama-cpp without adding USE flags for sparc

commit 9635629bd533f629e5fc052663d0935a2166338d
Author: Arniiiii <lg3dx6fd@gmail.com>
Date: Mon Feb 24 09:02:12 2025 +0000

update llama-cpp

commit e9bddea5f4830af196c8a9bc7f508b1a65f0b421
Author: Arniiiii <lg3dx6fd@gmail.com>
Date: Fri Feb 21 09:42:43 2025 +0000

add `RESTRICT="userpriv"` to llama-cpp ebuild.

now 94% tests are passed!

commit 93aa9392fb115eb38a8aba252406457cdf081536
Author: Arniiiii <lg3dx6fd@gmail.com>
Date: Sun Feb 9 10:46:49 2025 +0000

add some more docs

commit 6e01bd63e5f4f810647105b4071309ec9555cd7b
Author: Arniiiii <lg3dx6fd@gmail.com>
Date: Sun Feb 9 10:40:23 2025 +0000

attempt to fix tests for cuda and hip

commit cc6d3ca33e5258624f7a6f43e4830a9235b492e5
Author: Arniiiii <lg3dx6fd@gmail.com>
Date: Sun Feb 9 09:30:06 2025 +0000

update + fix `examples` use flag + new `cpu-native` use flag

commit 0b1ac3cfa55f10d7b2004cdd7c0e6b1e07650eaa
Author: Arniiiii <lg3dx6fd@gmail.com>
Date: Sun Feb 9 08:47:32 2025 +0000

make use of `cuda_src_prepare` only if USE `cuda`

commit a8975595cda53d58453ef9cd96796119ac0fbe1f
Author: Arniiiii <lg3dx6fd@gmail.com>
Date: Sun Feb 9 08:45:53 2025 +0000

make llama-cpp ebuild use `cuda` eclass

Now it requires manual overriding `NVCC_CCBIN=/usr/bin/gcc-13` or to
something else.

commit 6ef0fd7cedcad7cef374ed9caf2adc8a53d80321
Author: Arniiiii <lg3dx6fd@gmail.com>
Date: Sat Feb 8 12:25:48 2025 +0000

add new half-working ebuild for llama.cpp