The following sections describe how to build with different backends and options.
CPU Build
Build llama.cpp using CMake:
cmake -B build
cmake --build build --config Release
复制代码
Notes:
For faster compilation, add the -j argument to run multiple jobs in parallel, or use a generator that does this automatically such as Ninja. For example, cmake --build build --config Release -j 8 will run 8 jobs in parallel.
For faster repeated compilation, install ccache
For debug builds, there are two cases:
Single-config generators (e.g. default = Unix Makefiles; note that they just ignore the --config flag):
cmake -B build -DCMAKE_BUILD_TYPE=Debug
cmake --build build
复制代码
Multi-config generators (-G param set to Visual Studio, XCode...):
cmake -B build -G "Xcode"
cmake --build build --config Debug
复制代码
For more details and a list of supported generators, see the CMake documentation.
For static builds, add -DBUILD_SHARED_LIBS=OFF:
cmake -B build -DBUILD_SHARED_LIBS=OFF
cmake --build build --config Release
复制代码
Building for Windows (x86, x64 and arm64) with MSVC or clang as compilers:
Install Visual Studio 2022, e.g. via the Community Edition. In the installer, select at least the following options (this also automatically installs the required additional tools like CMake,...):
Tab Workload: Desktop-development with C++
Tab Components (select quickly via search): C++-CMake Tools for Windows, Git for Windows, C++-Clang Compiler for Windows, MS-Build Support for LLVM-Toolset (clang)
Please remember to always use a Developer Command Prompt / PowerShell for VS2022 for git, build, test
Building for arm64 can also be done with the MSVC compiler with the build-arm64-windows-MSVC preset, or the standard CMake build instructions. However, note that the MSVC compiler does not support inline ARM assembly code, used e.g. for the accelerated Q4_0_N_M CPU kernels.
For building with ninja generator and clang compiler as default: -set path:set LIB=C:\Program Files (x86)\Windows Kits\10\Lib\10.0.22621.0\um\x64;C:\Program Files\Microsoft Visual Studio\2022\Community\VC\Tools\MSVC\14.41.34120\lib\x64\uwp;C:\Program Files (x86)\Windows Kits\10\Lib\10.0.22621.0\ucrt\x64 bash cmake --preset x64-windows-llvm-release cmake --build build-x64-windows-llvm-release
BLAS Build
Building the program with BLAS support may lead to some performance improvements in prompt processing using batch sizes higher than 32 (the default is 512). Using BLAS doesn't affect the generation performance. There are currently several different BLAS implementations available for build and use:
Accelerate Framework
This is only available on Mac PCs and it's enabled by default. You can just build using the normal instructions.
OpenBLAS
This provides BLAS acceleration using only the CPU. Make sure to have OpenBLAS installed on your machine.
Building through oneAPI compilers will make avx_vnni instruction set available for intel processors that do not support avx512 and avx512_vnni. Please note that this build config does not support Intel GPU. For Intel GPU support, please refer to llama.cpp for SYCL.
Using manual oneAPI installation: By default, GGML_BLAS_VENDOR is set to Generic, so if you already sourced intel environment script and assign -DGGML_BLAS=ON in cmake, the mkl version of Blas will automatically been selected. Otherwise please install oneAPI and follow the below steps:
source /opt/intel/oneapi/setvars.sh # You can skip this step if in oneapi-basekit docker image, only required for manual installation
Using oneAPI docker image: If you do not want to source the environment vars and install oneAPI manually, you can also build the code using intel docker container: oneAPI-basekit. Then, you can use the commands given above.
Check Optimizing and Running LLaMA2 on Intel® CPU for more information.
Other BLAS libraries
Any other BLAS library can be used by setting the GGML_BLAS_VENDOR option. See the CMake documentation for a list of supported vendors.
Metal Build
On MacOS, Metal is enabled by default. Using Metal makes the computation run on the GPU. To disable the Metal build at compile time use the -DGGML_METAL=OFF cmake option.
When built with Metal support, you can explicitly disable GPU inference with the --n-gpu-layers 0 command-line argument.
SYCL
SYCL is a higher-level programming model to improve programming productivity on various hardware accelerators.
llama.cpp based on SYCL is used to support Intel GPU (Data Center Max series, Flex series, Arc series, Built-in GPU and iGPU).
For detailed info, please refer to llama.cpp for SYCL.
CUDA
This provides GPU acceleration using an NVIDIA GPU. Make sure to have the CUDA toolkit installed. You can download it from your Linux distro's package manager (e.g. apt install nvidia-cuda-toolkit) or from the NVIDIA developer site.
If you are using Fedora (using Fedora Workstation, or an 'Atomic' variant such as Silverblue), or would like to set up CUDA in a toolbox, please consider our Fedora CUDA guide. Unfortunately, the process is not as simple as one might expect.
Using CMake:
cmake -B build -DGGML_CUDA=ON
cmake --build build --config Release
复制代码
The environment variable CUDA_VISIBLE_DEVICES can be used to specify which GPU(s) will be used.
The environment variable GGML_CUDA_ENABLE_UNIFIED_MEMORY=1 can be used to enable unified memory in Linux. This allows swapping to system RAM instead of crashing when the GPU VRAM is exhausted. In Windows this setting is available in the NVIDIA control panel as System Memory Fallback.
The following compilation options are also available to tweak performance:
OptionLegal valuesDefaultDescriptionGGML_CUDA_FORCE_MMQBooleanfalseForce the use of custom matrix multiplication kernels for quantized models instead of FP16 cuBLAS even if there is no int8 tensor core implementation available (affects V100, RDNA3). MMQ kernels are enabled by default on GPUs with int8 tensor core support. With MMQ force enabled, speed for large batch sizes will be worse but VRAM consumption will be lower.GGML_CUDA_FORCE_CUBLASBooleanfalseForce the use of FP16 cuBLAS instead of custom matrix multiplication kernels for quantized modelsGGML_CUDA_F16BooleanfalseIf enabled, use half-precision floating point arithmetic for the CUDA dequantization + mul mat vec kernels and for the q4_1 and q5_1 matrix matrix multiplication kernels. Can improve performance on relatively recent GPUs.GGML_CUDA_PEER_MAX_BATCH_SIZEPositive integer128Maximum batch size for which to enable peer access between multiple GPUs. Peer access requires either Linux or NVLink. When using NVLink enabling peer access for larger batch sizes is potentially beneficial.GGML_CUDA_FA_ALL_QUANTSBooleanfalseCompile support for all KV cache quantization type (combinations) for the FlashAttention CUDA kernels. More fine-grained control over KV cache size but compilation takes much longer. MUSA
This provides GPU acceleration using the MUSA cores of your Moore Threads MTT GPU. Make sure to have the MUSA SDK installed. You can download it from here: MUSA SDK.
Using CMake:
cmake -B build -DGGML_MUSA=ON
cmake --build build --config Release
复制代码
The environment variable MUSA_VISIBLE_DEVICES can be used to specify which GPU(s) will be used.
The environment variable GGML_CUDA_ENABLE_UNIFIED_MEMORY=1 can be used to enable unified memory in Linux. This allows swapping to system RAM instead of crashing when the GPU VRAM is exhausted.
Most of the compilation options available for CUDA should also be available for MUSA, though they haven't been thoroughly tested yet.
HIP
This provides GPU acceleration on HIP-supported AMD GPUs. Make sure to have ROCm installed. You can download it from your Linux distro's package manager or from here: ROCm Quick Start (Linux).
Using CMake for Linux (assuming a gfx1030-compatible AMD GPU):
On Linux it is also possible to use unified memory architecture (UMA) to share main memory between the CPU and integrated GPU by setting -DGGML_HIP_UMA=ON. However, this hurts performance for non-integrated GPUs (but enables working with integrated GPUs).
Note that if you get the following error:
clang: error: cannot find ROCm device library; provide its path via '--rocm-path' or '--rocm-device-lib-path', or pass '-nogpulib' to build without ROCm device library
复制代码
Try searching for a directory under HIP_PATH that contains the file oclc_abi_version_400.bc. Then, add the following to the start of the command: HIP_DEVICE_LIB_PATH=<directory-you-just-found>, so something like:
Make sure that AMDGPU_TARGETS is set to the GPU arch you want to compile for. The above example uses gfx1100 that corresponds to Radeon RX 7900XTX/XT/GRE. You can find a list of targets here Find your gpu version string by matching the most significant version information from rocminfo | grep gfx | head -1 | awk '{print $2}' with the list of processors, e.g. gfx1035 maps to gfx1030.
The environment variable HIP_VISIBLE_DEVICES can be used to specify which GPU(s) will be used. If your GPU is not officially supported you can use the environment variable [HSA_OVERRIDE_GFX_VERSION] set to a similar GPU, for example 10.3.0 on RDNA2 (e.g. gfx1030, gfx1031, or gfx1035) or 11.0.0 on RDNA3.
Vulkan
Windows
w64devkit
Download and extract w64devkit.
Download and install the Vulkan SDK with the default settings.
Launch w64devkit.exe and run the following commands to copy Vulkan dependencies:
Switch into the llama.cpp directory and build using CMake.
cmake -B build -DGGML_VULKAN=ON
cmake --build build --config Release
复制代码
Git Bash MINGW64
Download and install Git-SCM with the default settings
Download and install Visual Studio Community Edition and make sure you select C++
Download and install CMake with the default settings
Download and install the Vulkan SDK with the default settings.
Go into your llama.cpp directory and right click, select Open Git Bash Here and then run the following commands
cmake -B build -DGGML_VULKAN=ON
cmake --build build --config Release
复制代码
Now you can load the model in conversation mode using Vulkan
# To verify the installation, use the command below:
vulkaninfo
复制代码
Alternatively your package manager might be able to provide the appropriate libraries. For example for Ubuntu 22.04 you can install libvulkan-dev instead. For Fedora 40, you can install vulkan-devel, glslc and glslang packages.
Then, build llama.cpp using the cmake command below:
cmake -B build -DGGML_VULKAN=1
cmake --build build --config Release
# Test the output binary (with "-ngl 33" to offload all layers to GPU)
./bin/llama-cli -m "PATH_TO_MODEL" -p "Hi you how are you" -n 50 -e -ngl 33 -t 4
# You should see in the output, ggml_vulkan detected your GPU. For example:
This provides NPU acceleration using the AI cores of your Ascend NPU. And CANN is a hierarchical APIs to help you to quickly build AI applications and service based on Ascend NPU.
For more information about Ascend NPU in Ascend Community.
Make sure to have the CANN toolkit installed. You can download it from here: CANN Toolkit
Go to llama.cpp directory and build using CMake.
For detailed info, such as model/device supports, CANN install, please refer to llama.cpp for CANN.
Android
To read documentation for how to build on Android, click here
Notes about GPU-accelerated backends
The GPU may still be used to accelerate some parts of the computation even when using the -ngl 0 option. You can fully disable GPU acceleration by using --device none.
In most cases, it is possible to build and use multiple backends at the same time. For example, you can build llama.cpp with both CUDA and Vulkan support by using the -DGGML_CUDA=ON -DGGML_VULKAN=ON options with CMake. At runtime, you can specify which backend devices to use with the --device option. To see a list of available devices, use the --list-devices option.
Backends can be built as dynamic libraries that can be loaded dynamically at runtime. This allows you to use the same llama.cpp binary on different machines with different GPUs. To enable this feature, use the GGML_BACKEND_DL option when building.