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

# CMake Build Options

> Complete reference for CMake configuration options in llama.cpp

## Overview

llama.cpp provides extensive CMake options to customize your build. Options are specified with `-D` flag:

```bash theme={null}
cmake -B build -DOPTION_NAME=VALUE
```

## General Options

### Build Type

| Option              | Values                                             | Default            | Description                              |
| ------------------- | -------------------------------------------------- | ------------------ | ---------------------------------------- |
| `CMAKE_BUILD_TYPE`  | `Debug`, `Release`, `RelWithDebInfo`, `MinSizeRel` | `Release`          | Build configuration type                 |
| `BUILD_SHARED_LIBS` | `ON`, `OFF`                                        | Platform-dependent | Build shared libraries instead of static |
| `GGML_STATIC`       | `ON`, `OFF`                                        | `OFF`              | Static link libraries                    |

```bash Debug build theme={null}
cmake -B build -DCMAKE_BUILD_TYPE=Debug
cmake --build build
```

```bash Static build theme={null}
cmake -B build -DBUILD_SHARED_LIBS=OFF
cmake --build build --config Release
```

### Optimization Options

| Option        | Values      | Default | Description                     |
| ------------- | ----------- | ------- | ------------------------------- |
| `GGML_NATIVE` | `ON`, `OFF` | `ON`    | Optimize for current system CPU |
| `GGML_LTO`    | `ON`, `OFF` | `OFF`   | Enable link-time optimization   |
| `GGML_CCACHE` | `ON`, `OFF` | `ON`    | Use ccache if available         |

<Note>
  `GGML_NATIVE=ON` optimizes for your current CPU but may not work on other systems.
</Note>

```bash Portable build (no native optimization) theme={null}
cmake -B build -DGGML_NATIVE=OFF
cmake --build build --config Release
```

### Build Targets

| Option                 | Values      | Default           | Description              |
| ---------------------- | ----------- | ----------------- | ------------------------ |
| `LLAMA_BUILD_TESTS`    | `ON`, `OFF` | `ON` (standalone) | Build test suite         |
| `LLAMA_BUILD_TOOLS`    | `ON`, `OFF` | `ON` (standalone) | Build command-line tools |
| `LLAMA_BUILD_EXAMPLES` | `ON`, `OFF` | `ON` (standalone) | Build example programs   |
| `LLAMA_BUILD_SERVER`   | `ON`, `OFF` | `ON` (standalone) | Build HTTP server        |
| `LLAMA_BUILD_COMMON`   | `ON`, `OFF` | `ON` (standalone) | Build common utilities   |

```bash Minimal build (library only) theme={null}
cmake -B build \
    -DLLAMA_BUILD_TESTS=OFF \
    -DLLAMA_BUILD_TOOLS=OFF \
    -DLLAMA_BUILD_EXAMPLES=OFF \
    -DLLAMA_BUILD_SERVER=OFF
cmake --build build --config Release
```

## GPU Backend Options

### CUDA (NVIDIA)

| Option                          | Values      | Default | Description                                  |
| ------------------------------- | ----------- | ------- | -------------------------------------------- |
| `GGML_CUDA`                     | `ON`, `OFF` | `OFF`   | Enable CUDA support                          |
| `GGML_CUDA_FORCE_MMQ`           | `ON`, `OFF` | `OFF`   | Force MMQ kernels instead of cuBLAS          |
| `GGML_CUDA_FORCE_CUBLAS`        | `ON`, `OFF` | `OFF`   | Force cuBLAS instead of custom kernels       |
| `GGML_CUDA_GRAPHS`              | `ON`, `OFF` | `ON`    | Enable CUDA graphs                           |
| `GGML_CUDA_FA`                  | `ON`, `OFF` | `ON`    | Compile FlashAttention kernels               |
| `GGML_CUDA_FA_ALL_QUANTS`       | `ON`, `OFF` | `OFF`   | Compile all quants for FlashAttention        |
| `GGML_CUDA_PEER_MAX_BATCH_SIZE` | Integer     | `128`   | Max batch size for peer access               |
| `GGML_CUDA_NO_PEER_COPY`        | `ON`, `OFF` | `OFF`   | Disable peer-to-peer copies                  |
| `GGML_CUDA_NO_VMM`              | `ON`, `OFF` | `OFF`   | Disable CUDA Virtual Memory Management       |
| `CMAKE_CUDA_ARCHITECTURES`      | String      | Auto    | Specify compute capabilities (e.g., "86;89") |

<CodeGroup>
  ```bash Basic CUDA theme={null}
  cmake -B build -DGGML_CUDA=ON
  cmake --build build --config Release
  ```

  ```bash CUDA with specific architectures theme={null}
  cmake -B build -DGGML_CUDA=ON -DCMAKE_CUDA_ARCHITECTURES="86;89"
  cmake --build build --config Release
  ```

  ```bash CUDA portable (all GPUs) theme={null}
  cmake -B build -DGGML_CUDA=ON -DGGML_NATIVE=OFF
  cmake --build build --config Release
  ```

  ```bash CUDA with FlashAttention all quants theme={null}
  cmake -B build -DGGML_CUDA=ON -DGGML_CUDA_FA_ALL_QUANTS=ON
  cmake --build build --config Release
  ```
</CodeGroup>

<Warning>
  `GGML_CUDA_FA_ALL_QUANTS=ON` significantly increases compilation time and binary size.
</Warning>

### HIP (AMD)

| Option                   | Values      | Default | Description                                |
| ------------------------ | ----------- | ------- | ------------------------------------------ |
| `GGML_HIP`               | `ON`, `OFF` | `OFF`   | Enable HIP support                         |
| `GGML_HIP_GRAPHS`        | `ON`, `OFF` | `OFF`   | Enable HIP graphs (experimental)           |
| `GGML_HIP_NO_VMM`        | `ON`, `OFF` | `ON`    | Disable HIP Virtual Memory Management      |
| `GGML_HIP_ROCWMMA_FATTN` | `ON`, `OFF` | `OFF`   | Enable rocWMMA for FlashAttention          |
| `GGML_HIP_MMQ_MFMA`      | `ON`, `OFF` | `ON`    | Enable MFMA MMA for CDNA in MMQ            |
| `GPU_TARGETS`            | String      | All     | Specify GPU architecture (e.g., "gfx1030") |

```bash Linux HIP build theme={null}
HIPCXX="$(hipconfig -l)/clang" HIP_PATH="$(hipconfig -R)" \
    cmake -B build -DGGML_HIP=ON -DGPU_TARGETS=gfx1030
cmake --build build --config Release
```

```bash Windows HIP build theme={null}
set PATH=%HIP_PATH%\bin;%PATH%
cmake -B build -G Ninja -DGGML_HIP=ON -DGPU_TARGETS=gfx1100 \
    -DCMAKE_C_COMPILER=clang -DCMAKE_CXX_COMPILER=clang++
cmake --build build
```

### Metal (Apple)

| Option                          | Values      | Default      | Description                       |
| ------------------------------- | ----------- | ------------ | --------------------------------- |
| `GGML_METAL`                    | `ON`, `OFF` | `ON` (macOS) | Enable Metal GPU support          |
| `GGML_METAL_NDEBUG`             | `ON`, `OFF` | `OFF`        | Disable Metal debugging           |
| `GGML_METAL_SHADER_DEBUG`       | `ON`, `OFF` | `OFF`        | Compile Metal with -fno-fast-math |
| `GGML_METAL_EMBED_LIBRARY`      | `ON`, `OFF` | `ON`         | Embed Metal library in binary     |
| `GGML_METAL_MACOSX_VERSION_MIN` | String      | Empty        | Metal minimum macOS version       |

```bash Disable Metal theme={null}
cmake -B build -DGGML_METAL=OFF
cmake --build build --config Release
```

### Vulkan

| Option                      | Values      | Default | Description                     |
| --------------------------- | ----------- | ------- | ------------------------------- |
| `GGML_VULKAN`               | `ON`, `OFF` | `OFF`   | Enable Vulkan support           |
| `GGML_VULKAN_CHECK_RESULTS` | `ON`, `OFF` | `OFF`   | Run Vulkan operation checks     |
| `GGML_VULKAN_DEBUG`         | `ON`, `OFF` | `OFF`   | Enable Vulkan debug output      |
| `GGML_VULKAN_MEMORY_DEBUG`  | `ON`, `OFF` | `OFF`   | Enable Vulkan memory debug      |
| `GGML_VULKAN_VALIDATE`      | `ON`, `OFF` | `OFF`   | Enable Vulkan validation layers |

```bash Vulkan with validation theme={null}
cmake -B build -DGGML_VULKAN=ON -DGGML_VULKAN_VALIDATE=ON
cmake --build build --config Release
```

### SYCL (Intel GPU)

| Option             | Values      | Default | Description                        |
| ------------------ | ----------- | ------- | ---------------------------------- |
| `GGML_SYCL`        | `ON`, `OFF` | `OFF`   | Enable SYCL support                |
| `GGML_SYCL_F16`    | `ON`, `OFF` | `OFF`   | Use 16-bit floats for calculations |
| `GGML_SYCL_GRAPH`  | `ON`, `OFF` | `ON`    | Enable graphs in SYCL backend      |
| `GGML_SYCL_DNN`    | `ON`, `OFF` | `ON`    | Enable oneDNN in SYCL backend      |
| `GGML_SYCL_TARGET` | String      | `INTEL` | SYCL target device                 |

```bash theme={null}
cmake -B build -DGGML_SYCL=ON -DGGML_SYCL_F16=ON
cmake --build build --config Release
```

## CPU Backend Options

### BLAS Libraries

| Option             | Values      | Default      | Description                                        |
| ------------------ | ----------- | ------------ | -------------------------------------------------- |
| `GGML_BLAS`        | `ON`, `OFF` | `OFF`        | Enable BLAS support                                |
| `GGML_BLAS_VENDOR` | String      | `Generic`    | BLAS vendor (OpenBLAS, Intel10\_64lp, Apple, etc.) |
| `GGML_ACCELERATE`  | `ON`, `OFF` | `ON` (macOS) | Use Accelerate framework                           |

<CodeGroup>
  ```bash OpenBLAS theme={null}
  cmake -B build -DGGML_BLAS=ON -DGGML_BLAS_VENDOR=OpenBLAS
  cmake --build build --config Release
  ```

  ```bash Intel MKL theme={null}
  source /opt/intel/oneapi/setvars.sh
  cmake -B build -DGGML_BLAS=ON -DGGML_BLAS_VENDOR=Intel10_64lp \
      -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx
  cmake --build build --config Release
  ```

  ```bash Apple Accelerate (default on macOS) theme={null}
  cmake -B build
  cmake --build build --config Release
  ```
</CodeGroup>

### CPU Instruction Sets

| Option             | Values      | Default | Description            |
| ------------------ | ----------- | ------- | ---------------------- |
| `GGML_SSE42`       | `ON`, `OFF` | `ON`\*  | Enable SSE 4.2         |
| `GGML_AVX`         | `ON`, `OFF` | `ON`\*  | Enable AVX             |
| `GGML_AVX2`        | `ON`, `OFF` | `ON`\*  | Enable AVX2            |
| `GGML_AVX_VNNI`    | `ON`, `OFF` | `OFF`   | Enable AVX-VNNI        |
| `GGML_AVX512`      | `ON`, `OFF` | `OFF`   | Enable AVX-512F        |
| `GGML_AVX512_VBMI` | `ON`, `OFF` | `OFF`   | Enable AVX-512 VBMI    |
| `GGML_AVX512_VNNI` | `ON`, `OFF` | `OFF`   | Enable AVX-512 VNNI    |
| `GGML_AVX512_BF16` | `ON`, `OFF` | `OFF`   | Enable AVX-512 BF16    |
| `GGML_FMA`         | `ON`, `OFF` | `ON`\*  | Enable FMA (non-MSVC)  |
| `GGML_F16C`        | `ON`, `OFF` | `ON`\*  | Enable F16C (non-MSVC) |
| `GGML_BMI2`        | `ON`, `OFF` | `ON`\*  | Enable BMI2            |

\* Default is `ON` unless `GGML_NATIVE=OFF`

<Warning>
  These options override automatic detection. Only use if you know your target CPU capabilities.
</Warning>

```bash Enable AVX-512 theme={null}
cmake -B build -DGGML_AVX512=ON -DGGML_AVX512_VNNI=ON
cmake --build build --config Release
```

### ARM CPU Options

| Option              | Values      | Default | Description                    |
| ------------------- | ----------- | ------- | ------------------------------ |
| `GGML_CPU_KLEIDIAI` | `ON`, `OFF` | `OFF`   | Use KleidiAI optimized kernels |
| `GGML_CPU_ARM_ARCH` | String      | Empty   | CPU architecture for ARM       |
| `GGML_RVV`          | `ON`, `OFF` | `ON`    | Enable RISC-V vector extension |

```bash Arm KleidiAI theme={null}
cmake -B build -DGGML_CPU_KLEIDIAI=ON
cmake --build build --config Release
```

## Special Purpose Backends

### CANN (Ascend NPU)

```bash theme={null}
cmake -B build -DGGML_CANN=ON
cmake --build build --config Release
```

### ZenDNN (AMD EPYC)

| Option        | Values      | Default | Description                 |
| ------------- | ----------- | ------- | --------------------------- |
| `GGML_ZENDNN` | `ON`, `OFF` | `OFF`   | Enable ZenDNN support       |
| `ZENDNN_ROOT` | Path        | Empty   | Path to ZenDNN installation |

```bash theme={null}
cmake -B build -DGGML_ZENDNN=ON
cmake --build build --config Release
```

### OpenCL (Qualcomm Adreno)

| Option                           | Values      | Default | Description                  |
| -------------------------------- | ----------- | ------- | ---------------------------- |
| `GGML_OPENCL`                    | `ON`, `OFF` | `OFF`   | Enable OpenCL support        |
| `GGML_OPENCL_PROFILING`          | `ON`, `OFF` | `OFF`   | Enable OpenCL profiling      |
| `GGML_OPENCL_EMBED_KERNELS`      | `ON`, `OFF` | `ON`    | Embed kernels in binary      |
| `GGML_OPENCL_USE_ADRENO_KERNELS` | `ON`, `OFF` | `ON`    | Use optimized Adreno kernels |

```bash theme={null}
cmake -B build -DGGML_OPENCL=ON
cmake --build build --config Release
```

### RPC Backend

```bash theme={null}
cmake -B build -DGGML_RPC=ON
cmake --build build --config Release
```

## Advanced Options

### Threading

| Option        | Values      | Default | Description                 |
| ------------- | ----------- | ------- | --------------------------- |
| `GGML_OPENMP` | `ON`, `OFF` | `ON`    | Enable OpenMP for threading |

```bash Disable OpenMP theme={null}
cmake -B build -DGGML_OPENMP=OFF
cmake --build build --config Release
```

### Debugging & Diagnostics

| Option                     | Values      | Default | Description                         |
| -------------------------- | ----------- | ------- | ----------------------------------- |
| `LLAMA_ALL_WARNINGS`       | `ON`, `OFF` | `ON`    | Enable all compiler warnings        |
| `LLAMA_FATAL_WARNINGS`     | `ON`, `OFF` | `OFF`   | Treat warnings as errors            |
| `LLAMA_SANITIZE_THREAD`    | `ON`, `OFF` | `OFF`   | Enable thread sanitizer             |
| `LLAMA_SANITIZE_ADDRESS`   | `ON`, `OFF` | `OFF`   | Enable address sanitizer            |
| `LLAMA_SANITIZE_UNDEFINED` | `ON`, `OFF` | `OFF`   | Enable undefined behavior sanitizer |

```bash Build with sanitizers theme={null}
cmake -B build -DCMAKE_BUILD_TYPE=Debug \
    -DLLAMA_SANITIZE_ADDRESS=ON \
    -DLLAMA_SANITIZE_UNDEFINED=ON
cmake --build build
```

### Backend Dynamic Loading

| Option             | Values      | Default | Description                         |
| ------------------ | ----------- | ------- | ----------------------------------- |
| `GGML_BACKEND_DL`  | `ON`, `OFF` | `OFF`   | Build backends as dynamic libraries |
| `GGML_BACKEND_DIR` | Path        | Empty   | Directory to load backends from     |

<Note>
  `GGML_BACKEND_DL` requires `BUILD_SHARED_LIBS=ON`.
</Note>

```bash Dynamic backend loading theme={null}
cmake -B build -DBUILD_SHARED_LIBS=ON -DGGML_BACKEND_DL=ON
cmake --build build --config Release
```

### HTTPS/SSL Support

| Option          | Values      | Default | Description                   |
| --------------- | ----------- | ------- | ----------------------------- |
| `LLAMA_OPENSSL` | `ON`, `OFF` | `ON`    | Use OpenSSL for HTTPS support |

```bash Disable OpenSSL theme={null}
cmake -B build -DLLAMA_OPENSSL=OFF
cmake --build build --config Release
```

## Common Build Configurations

### Development Build

Fast compilation, full debug info:

```bash theme={null}
cmake -B build -DCMAKE_BUILD_TYPE=Debug \
    -DLLAMA_ALL_WARNINGS=ON
cmake --build build
```

### Production Build

Optimized for performance:

```bash theme={null}
cmake -B build -DCMAKE_BUILD_TYPE=Release \
    -DGGML_NATIVE=ON \
    -DGGML_LTO=ON \
    -DBUILD_SHARED_LIBS=OFF
cmake --build build --config Release
```

### Multi-GPU Build

CUDA + Vulkan for flexibility:

```bash theme={null}
cmake -B build -DGGML_CUDA=ON -DGGML_VULKAN=ON \
    -DGGML_CUDA_GRAPHS=ON
cmake --build build --config Release
```

### Minimal Binary Size

Library only, static linking:

```bash theme={null}
cmake -B build -DCMAKE_BUILD_TYPE=MinSizeRel \
    -DBUILD_SHARED_LIBS=OFF \
    -DLLAMA_BUILD_TESTS=OFF \
    -DLLAMA_BUILD_TOOLS=OFF \
    -DLLAMA_BUILD_EXAMPLES=OFF \
    -DLLAMA_BUILD_SERVER=OFF
cmake --build build --config MinSizeRel
```

### Portable Build

Runs on any x86\_64 system:

```bash theme={null}
cmake -B build -DGGML_NATIVE=OFF \
    -DGGML_AVX=ON \
    -DGGML_AVX2=ON \
    -DGGML_FMA=ON \
    -DBUILD_SHARED_LIBS=OFF
cmake --build build --config Release
```

## Option Discovery

To see all available CMake options:

```bash theme={null}
cmake -B build -LH
```

To see current configuration:

```bash theme={null}
cmake -B build -LA
```

For GUI-based configuration (requires cmake-gui):

```bash theme={null}
cmake-gui -B build
```