Last active
September 19, 2024 21:19
-
-
Save SteelPh0enix/8651ed5a6ea571b1cd11b8c9fa47ac47 to your computer and use it in GitHub Desktop.
Script for building llama.cpp under Windows for ROCm
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| REM execute via VS native tools command line prompt | |
| REM make sure to clone the repo first, put this script next to the repo dir | |
| REM this script is configured for building llama.cpp w/ ROCm support | |
| REM for a system with Ryzen 9 5900X and RX 7900XT. | |
| REM Unless you have the exact same setup, you may need to change some flags | |
| REM and/or strings here. | |
| set AMDGPU_TARGETS="gfx1100" | |
| set HSA_OVERRIDE_GFX_VERSION="11.0.0" | |
| set ROCM_VERSION="6.1.2" | |
| set USE_ROCM=1 | |
| set ROCM_PATH=%HIP_PATH% | |
| set CMAKE_MODULE_PATH=%HIP_PATH%cmake;%CMAKE_MODULE_PATH% | |
| set CMAKE_PREFIX_PATH=%ROCM_PATH%;%CMAKE_PREFIX_PATH% | |
| set PATH=%ROCM_PATH%bin;%PATH% | |
| set LLAMA_CPP_PYTHON_VENV_PATH=%USERPROFILE%\.llama.cpp.venv | |
| call %LLAMA_CPP_PYTHON_VENV_PATH%\Scripts\activate.bat | |
| cd %HOMEPATH%\.llama.cpp | |
| git clean -xddf | |
| git pull | |
| git submodule update --recursive | |
| git lfs pull | |
| REM update Python dependencies | |
| python -m pip install --upgrade pip setuptools wheel | |
| python -m pip install --upgrade sentencepiece transformers protobuf torch | |
| REM you may want to enable CCACHE, i don't want it. | |
| cmake -S . -B build -G Ninja^ | |
| -DCMAKE_BUILD_TYPE=Release^ | |
| -DCMAKE_CXX_COMPILER=clang++^ | |
| -DCMAKE_C_COMPILER=clang^ | |
| -DLLAMA_BUILD_TESTS=OFF^ | |
| -DLLAMA_BUILD_EXAMPLES=ON^ | |
| -DLLAMA_BUILD_SERVER=ON^ | |
| -DLLAMA_STANDALONE=ON^ | |
| -DLLAMA_CURL=OFF^ | |
| -DGGML_CCACHE=OFF^ | |
| -DGGML_NATIVE=ON^ | |
| -DGGML_LTO=ON^ | |
| -DGGML_AVX=ON^ | |
| -DGGML_AVX2=ON^ | |
| -DGGML_FMA=ON^ | |
| -DGGML_OPENMP=ON^ | |
| -DAMDGPU_TARGETS=%AMDGPU_TARGETS%^ | |
| -DGGML_HIPBLAS=ON^ | |
| -DGGML_CUDA_DMMV_X=1026^ | |
| -DGGML_CUDA_MMV_Y=64^ | |
| -DGGML_CUDA_GRAPHS=ON | |
| cmake --build build --config Release --parallel 24 | |
| cd .. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment