vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Rename LLAMA_CUBLAS flag to LLAMA_CUDA in fulfilment of the prophecy.

Browse source 
This is being changed in Make.
https://github.com/ggerganov/llama.cpp/pull/6299
This commit is contained in:
JohnnyB 2024-03-25 18:16:19 +00:00 • committed by GitHub
parent b06c16ef9f
commit 7c5ad052af
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
.devops/llama-cpp-cublas.srpm.spec
View file

@ -32,7 +32,7 @@ CPU inference for Meta's Lllama2 models using default options.
%setup -n llama.cpp-master
%build
make -j LLAMA_CUBLAS=1
make -j LLAMA_CUDA=1
%install
mkdir -p %{buildroot}%{_bindir}/