> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/ggml-org/ggml/llms.txt
> Use this file to discover all available pages before exploring further.

# Building ggml

> Compile ggml with different backends and options.

## Prerequisites

* **CMake** 3.14 or later
* A C11 / C++17 compiler: GCC, Clang, or MSVC
* **Git**

Backend-specific requirements are listed in the relevant sections below.

## Basic build

```bash theme={null}
git clone https://github.com/ggml-org/ggml
cd ggml
mkdir build && cd build
cmake ..
cmake --build . --config Release -j 8
```

This produces the core `ggml` library and all examples in `build/bin/`. The
default build targets the CPU backend with native ISA optimizations enabled.

## Backend builds

<Tabs>
  <Tab title="CUDA">
    <Note>
      Requires the NVIDIA CUDA Toolkit (tested with CUDA 11.x and 12.x) and a
      compatible NVIDIA GPU. Ensure `nvcc` is on your `PATH`.
    </Note>

    ```bash theme={null}
    cmake .. -DGGML_CUDA=ON
    cmake --build . --config Release -j 8
    ```

    Additional CUDA options:

    | Flag                     | Default | Description                              |
    | ------------------------ | ------- | ---------------------------------------- |
    | `GGML_CUDA_FORCE_MMQ`    | `OFF`   | Use MMQ kernels instead of cuBLAS        |
    | `GGML_CUDA_FORCE_CUBLAS` | `OFF`   | Always use cuBLAS instead of MMQ kernels |
    | `GGML_CUDA_FA`           | `ON`    | Compile FlashAttention CUDA kernels      |
    | `GGML_CUDA_GRAPHS`       | `OFF`   | Enable CUDA graph capture (llama.cpp)    |
    | `GGML_CUDA_NO_VMM`       | `OFF`   | Disable CUDA virtual memory management   |

    ```bash theme={null}
    # Example: CUDA with cuBLAS forced on and FlashAttention for all quants
    cmake .. -DGGML_CUDA=ON \
             -DGGML_CUDA_FORCE_CUBLAS=ON \
             -DGGML_CUDA_FA_ALL_QUANTS=ON
    ```
  </Tab>

  <Tab title="Metal">
    <Note>
      Metal is enabled by default on Apple platforms. macOS 12.3 or later is
      recommended. The build requires Xcode Command Line Tools.
    </Note>

    ```bash theme={null}
    cmake .. -DGGML_METAL=ON
    cmake --build . --config Release -j 8
    ```

    By default the Metal shader library is embedded into the binary
    (`GGML_METAL_EMBED_LIBRARY=ON`). To disable embedding:

    ```bash theme={null}
    cmake .. -DGGML_METAL=ON -DGGML_METAL_EMBED_LIBRARY=OFF
    ```

    Additional Metal options:

    | Flag                            | Default | Description                         |
    | ------------------------------- | ------- | ----------------------------------- |
    | `GGML_METAL_NDEBUG`             | `OFF`   | Disable Metal debugging             |
    | `GGML_METAL_SHADER_DEBUG`       | `OFF`   | Compile Metal with `-fno-fast-math` |
    | `GGML_METAL_MACOSX_VERSION_MIN` | \`\`    | Minimum macOS deployment target     |
  </Tab>

  <Tab title="Vulkan">
    <Warning>
      Vulkan support requires the [Vulkan SDK](https://vulkan.lunarg.com/)
      to be installed and `VULKAN_SDK` to be set in your environment.
    </Warning>

    ```bash theme={null}
    cmake .. -DGGML_VULKAN=ON
    cmake --build . --config Release -j 8
    ```

    Additional Vulkan options:

    | Flag                        | Default | Description                     |
    | --------------------------- | ------- | ------------------------------- |
    | `GGML_VULKAN_CHECK_RESULTS` | `OFF`   | Run op correctness checks       |
    | `GGML_VULKAN_DEBUG`         | `OFF`   | Enable Vulkan debug output      |
    | `GGML_VULKAN_VALIDATE`      | `OFF`   | Enable Vulkan validation layers |
    | `GGML_VULKAN_MEMORY_DEBUG`  | `OFF`   | Enable memory debug output      |
  </Tab>

  <Tab title="HIP (AMD)">
    <Warning>
      Requires ROCm 5.x or later. Set `CMAKE_PREFIX_PATH` or
      `ROCM_PATH` to your ROCm installation directory before configuring.
    </Warning>

    ```bash theme={null}
    cmake .. -DGGML_HIP=ON
    cmake --build . --config Release -j 8
    ```

    Additional HIP options:

    | Flag                     | Default | Description                             |
    | ------------------------ | ------- | --------------------------------------- |
    | `GGML_HIP_GRAPHS`        | `OFF`   | Enable HIP graph capture (experimental) |
    | `GGML_HIP_ROCWMMA_FATTN` | `OFF`   | Enable rocWMMA for FlashAttention       |
    | `GGML_HIP_MMQ_MFMA`      | `ON`    | Enable MFMA MMA for CDNA in MMQ         |
  </Tab>
</Tabs>

## General CMake options

These options apply to all build configurations.

| Flag                | Default | Description                                    |
| ------------------- | ------- | ---------------------------------------------- |
| `GGML_STATIC`       | `OFF`   | Static link libraries                          |
| `GGML_NATIVE`       | `ON`    | Optimize for the host CPU (enables AVX2, etc.) |
| `GGML_LTO`          | `OFF`   | Enable link-time optimization                  |
| `GGML_CCACHE`       | `ON`    | Use ccache if available                        |
| `GGML_BACKEND_DL`   | `OFF`   | Build backends as dynamic libraries            |
| `BUILD_SHARED_LIBS` | `ON`    | Build shared instead of static libraries       |
| `GGML_OPENMP`       | `ON`    | Use OpenMP for CPU multi-threading             |

## CPU instruction set options

<Note>
  When `GGML_NATIVE=ON` (the default), the compiler detects and enables all
  supported ISA extensions automatically. Set individual flags only when
  cross-compiling or targeting a specific baseline.
</Note>

| Flag          | Description     |
| ------------- | --------------- |
| `GGML_AVX`    | Enable AVX      |
| `GGML_AVX2`   | Enable AVX2     |
| `GGML_AVX512` | Enable AVX-512F |
| `GGML_FMA`    | Enable FMA      |
| `GGML_F16C`   | Enable F16C     |
| `GGML_SSE42`  | Enable SSE 4.2  |
| `GGML_BMI2`   | Enable BMI2     |

Example — build for a fixed AVX2 baseline without native detection:

```bash theme={null}
cmake .. -DGGML_NATIVE=OFF \
         -DGGML_AVX=ON \
         -DGGML_AVX2=ON \
         -DGGML_FMA=ON \
         -DGGML_F16C=ON
```