thek0tyara/llama-cpp-turboquant
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 6

1:7127-alt1

Browse source 
- Update to b7127 (2025-11-21).
- spec: Remove llama.cpp-convert package.
- model: detect GigaChat3-10-A1.8B as deepseek lite.
This commit is contained in:
Vitaly Chikunov 2025-11-21 18:40:56 +00:00
parent 6ccc09a99d
commit bbb4f595fe
2 changed files with 7 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

7
.gear/llama.cpp.spec
View file

@ -11,7 +11,7 @@
%def_with vulkan
Name: llama.cpp
Version: 6869
Version: 7127
Release: alt1
Epoch: 1
Summary: LLM inference in C/C++
@ -261,6 +261,11 @@ mv %buildroot%_bindir/convert*.py -t %buildroot%_datadir/%name/examples
%endif
%changelog
* Fri Nov 21 2025 Vitaly Chikunov <vt@altlinux.org> 1:7127-alt1
- Update to b7127 (2025-11-21).
- spec: Remove llama.cpp-convert package.
- model: detect GigaChat3-10-A1.8B as deepseek lite.
* Tue Oct 28 2025 Vitaly Chikunov <vt@altlinux.org> 1:6869-alt1
- Update to b6869 (2025-10-28).

2
.gear/tags/list
View file

@ -1 +1 @@
851553ea6b24cb39fd5fd188b437d777cb411de8 b6869
23bc779a6e58762ea892eca1801b2ea1b9050c00 b7127