Remove references to FORCE_CMAKE

Makefile

@@ -13,19 +13,19 @@ build:
 	python3 -m pip install -e .
 
 build.cuda:
-	CMAKE_ARGS="-DLLAMA_CUBLAS=on" FORCE_CMAKE=1 python3 -m pip install -e .
+	CMAKE_ARGS="-DLLAMA_CUBLAS=on" python3 -m pip install -e .
 
 build.opencl:
-	CMAKE_ARGS="-DLLAMA_CLBLAST=on" FORCE_CMAKE=1 python3 -m pip install -e .
+	CMAKE_ARGS="-DLLAMA_CLBLAST=on" python3 -m pip install -e .
 
 build.openblas:
-	CMAKE_ARGS="-DLLAMA_CLBLAST=on" FORCE_CMAKE=1 python3 -m pip install -e .
+	CMAKE_ARGS="-DLLAMA_CLBLAST=on" python3 -m pip install -e .
 
 build.blis:
-	CMAKE_ARGS="-DLLAMA_OPENBLAS=on -DLLAMA_OPENBLAS_VENDOR=blis" FORCE_CMAKE=1 python3 -m pip install -e .
+	CMAKE_ARGS="-DLLAMA_OPENBLAS=on -DLLAMA_OPENBLAS_VENDOR=blis" python3 -m pip install -e .
 
 build.metal:
-	CMAKE_ARGS="-DLLAMA_METAL=on" FORCE_CMAKE=1 python3 -m pip install -e .
+	CMAKE_ARGS="-DLLAMA_METAL=on" python3 -m pip install -e .
 
 build.sdist:
 	python3 -m build --sdist

README.md

@@ -48,36 +48,35 @@ Otherwise, while installing it will build the llama.ccp x86 version which will b
 ### Installation with Hardware Acceleration
 
 `llama.cpp` supports multiple BLAS backends for faster processing.
-Use the `FORCE_CMAKE=1` environment variable to force the use of `cmake` and install the pip package for the desired BLAS backend.
 
 To install with OpenBLAS, set the `LLAMA_BLAS and LLAMA_BLAS_VENDOR` environment variables before installing:
 
 ```bash
-CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" FORCE_CMAKE=1 pip install llama-cpp-python
+CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" pip install llama-cpp-python
 ```
 
 To install with cuBLAS, set the `LLAMA_CUBLAS=1` environment variable before installing:
 
 ```bash
-CMAKE_ARGS="-DLLAMA_CUBLAS=on" FORCE_CMAKE=1 pip install llama-cpp-python
+CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python
 ```
 
 To install with CLBlast, set the `LLAMA_CLBLAST=1` environment variable before installing:
 
 ```bash
-CMAKE_ARGS="-DLLAMA_CLBLAST=on" FORCE_CMAKE=1 pip install llama-cpp-python
+CMAKE_ARGS="-DLLAMA_CLBLAST=on" pip install llama-cpp-python
 ```
 
 To install with Metal (MPS), set the `LLAMA_METAL=on` environment variable before installing:
 
 ```bash
-CMAKE_ARGS="-DLLAMA_METAL=on" FORCE_CMAKE=1 pip install llama-cpp-python
+CMAKE_ARGS="-DLLAMA_METAL=on" pip install llama-cpp-python
 ```
 
 To install with hipBLAS / ROCm support for AMD cards, set the `LLAMA_HIPBLAS=on` environment variable before installing:
 
 ```bash
-CMAKE_ARGS="-DLLAMA_HIPBLAS=on" FORCE_CMAKE=1 pip install llama-cpp-python
+CMAKE_ARGS="-DLLAMA_HIPBLAS=on" pip install llama-cpp-python
 ```
 
 #### Windows remarks

docker/cuda_simple/Dockerfile

@@ -21,7 +21,7 @@ ENV LLAMA_CUBLAS=1
 RUN python3 -m pip install --upgrade pip pytest cmake scikit-build setuptools fastapi uvicorn sse-starlette pydantic-settings
 
 # Install llama-cpp-python (build with cuda)
-RUN CMAKE_ARGS="-DLLAMA_CUBLAS=on" FORCE_CMAKE=1 pip install llama-cpp-python
+RUN CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python
 
 # Run the server
 CMD python3 -m llama_cpp.server

docs/install/macos.md

@@ -30,7 +30,7 @@ conda activate llama
     *(you needed xcode installed in order pip to build/compile the C++ code)*
 ```
 pip uninstall llama-cpp-python -y
-CMAKE_ARGS="-DLLAMA_METAL=on" FORCE_CMAKE=1 pip install -U llama-cpp-python --no-cache-dir
+CMAKE_ARGS="-DLLAMA_METAL=on" pip install -U llama-cpp-python --no-cache-dir
 pip install 'llama-cpp-python[server]'
 
 # you should now have llama-cpp-python v0.1.62 or higher installed