thek0tyara/llama-cpp-turboquant
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 4

1:5332-alt1

Browse source 
- Update to b5332 (2025-05-09), with vision support in llama-server.
- Enable Vulkan backend (for GPU) in llama.cpp-vulkan package.
This commit is contained in:
Vitaly Chikunov 2025-05-10 02:13:53 +03:00
parent 2969e4c10c
commit 66330c5eaa
2 changed files with 4 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

6
.gear/llama.cpp.spec
View file

@ -11,7 +11,7 @@
%def_with vulkan
Name: llama.cpp
Version: 5318
Version: 5332
Release: alt1
Epoch: 1
Summary: LLM inference in C/C++
@ -251,8 +251,8 @@ llama-cli -m %_datadir/tinyllamas/stories260K.gguf -p "Once upon a time" -s 55 -
%endif
%changelog
* Fri May 09 2025 Vitaly Chikunov <vt@altlinux.org> 1:5318-alt1
- Update to b5318 (2025-05-08).
* Sat May 10 2025 Vitaly Chikunov <vt@altlinux.org> 1:5332-alt1
- Update to b5332 (2025-05-09), with vision support in llama-server.
- Enable Vulkan backend (for GPU) in llama.cpp-vulkan package.
* Mon Mar 10 2025 Vitaly Chikunov <vt@altlinux.org> 1:4855-alt1

2
.gear/tags/list
View file

@ -1,2 +1,2 @@
4565194ed7c32d1d2efa32ceab4d3c6cae006306 submodule/kompute-0
15e03282bb432631193464100c2237a3b6bcfe4c b5318
7c28a74e0783f4bb74a246fb9f19bf212139e365 b5332