Update cuda.Dockerfile

Docker/cuda/cuda.Dockerfile

@@ -30,13 +30,13 @@ COPY --chown=myuser:myuser . .
 
 # Setting build-related environment variables
 ENV CUDA_DOCKER_ARCH=all
-ENV LLAMA_CUBLAS=1
+ENV GGML_CUDA=1
 
 # Install Python dependencies
 RUN python3 -m pip install --upgrade pip pytest cmake scikit-build setuptools fastapi uvicorn sse-starlette pydantic-settings starlette-context
 
 # Install llama-cpp-python (build with CUDA)
-RUN CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python
+RUN CMAKE_ARGS="-DGGML_CUDA=on" pip install llama-cpp-python
 
 # Expose the port
 EXPOSE 8008