Merge pull request #704 from axel7083/fix/cuda-build

fix(modell_server): deprecated make arguments for llamacpp server

Author: rhatdan

model_servers/llamacpp_python/cuda/Containerfile

@@ -4,7 +4,7 @@ RUN  dnf install -y gcc-toolset-13-gcc gcc-toolset-13-gcc-c++
 USER 1001
 WORKDIR /locallm
 COPY src .
-ENV CMAKE_ARGS="-DLLAMA_CUBLAS=on -DLLAMA_AVX2=OFF -DLLAMA_FMA=OFF -DLLAMA_F16C=OFF"
+ENV CMAKE_ARGS="-DGGML_CUDA=on -DLLAMA_AVX2=OFF -DLLAMA_FMA=OFF -DLLAMA_F16C=OFF"
 ENV FORCE_CMAKE=1
 RUN CC="/opt/rh/gcc-toolset-13/root/usr/bin/gcc" CXX="/opt/rh/gcc-toolset-13/root/usr/bin/g++" pip install --no-cache-dir -r ./requirements.txt
 ENTRYPOINT [ "sh", "run.sh" ]