Back to Ollama

Development

docs/development.md

0.30.05.7 KB
Original Source

Development

Install prerequisites:

  • Go
  • CMake 3.24 or newer
  • C/C++ compiler: Clang on macOS, Visual Studio 2022 C++ tools on Windows, or GCC/Clang on Linux
  • Ninja in PATH is recommended, especially on Windows

For pure Go iteration against an existing native payload, run Ollama from the repository root:

shell
go run . serve

[!NOTE] Ollama includes native code compiled with CGO. From time to time these data structures can change and CGO can get out of sync resulting in unexpected crashes. You can force a full build of the native code by running go clean -cache first.

Native build model

For a fresh checkout, or after changing native code, build from the repository root. On macOS arm64, this builds Metal inference. On all other platforms this builds CPU-only inference. It builds the Go binary at the repository root and installs the native runtime payload under build/lib/ollama.

shell
cmake -B build .
cmake --build build --parallel 8
./ollama serve

To install into a standard prefix layout:

shell
cmake --install build --prefix /path/to/install

On all platforms except macOS arm64, to build GPU backends select the backends explicitly:

shell
cmake -B build . -DOLLAMA_LLAMA_BACKENDS="cuda_v13;vulkan"
cmake --build build --parallel 8

Supported backend values are cuda_v12, cuda_v13, rocm_v7_1, rocm_v7_2, vulkan, cuda_jetpack5, and cuda_jetpack6.

Use standard CMake architecture overrides to narrow GPU builds for local hardware:

shell
# CUDA
cmake -B build . -DOLLAMA_LLAMA_BACKENDS=cuda_v13 -DCMAKE_CUDA_ARCHITECTURES=native

# ROCm / HIP
cmake -B build . -DOLLAMA_LLAMA_BACKENDS=rocm_v7_2 -DCMAKE_HIP_ARCHITECTURES=gfx1100

You can tune GGML build options by setting GGML_* values during configure. For example, to build CUDA v12 for Pascal without flash attention kernels:

shell
cmake -B build . -DOLLAMA_LLAMA_BACKENDS=cuda_v12 -DCMAKE_CUDA_ARCHITECTURES=61 -DGGML_CUDA_FA=OFF

macOS (Apple Silicon)

Additional prerequisites:

MLX Metal requires the Metal toolchain. Install Xcode first, then:

shell
xcodebuild -downloadComponent MetalToolchain

Windows

Additional prerequisites:

For Ninja builds, run CMake from a Developer PowerShell/Command Prompt or another shell where the Visual Studio compiler is available.

Building for Vulkan requires VULKAN_SDK environment variable:

PowerShell

powershell
$env:VULKAN_SDK="C:\VulkanSDK\<version>"

CMD

cmd
set VULKAN_SDK=C:\VulkanSDK\<version>

Windows (ARM)

Windows ARM does not support additional acceleration libraries at this time.

Linux

Additional prerequisites:

  • (Optional) AMD GPU support
  • (Optional) NVIDIA GPU support
  • (Optional) Vulkan GPU support
    • Vulkan SDK - useful for AMD/Intel GPUs
    • Or install via package manager: sudo apt install vulkan-sdk (Ubuntu/Debian) or sudo dnf install vulkan-sdk (Fedora/CentOS)
  • (Optional) MLX engine support
    • CUDA 13+ SDK
    • cuDNN 9+
    • OpenBLAS/LAPACK: sudo apt install libopenblas-dev liblapack-dev liblapacke-dev (Ubuntu/Debian)

[!IMPORTANT] Ensure prerequisites are in PATH before running CMake.

MLX Engine (Optional)

The MLX engine enables running safetensor based models. On macOS arm64, MLX is enabled by default. On other platforms, MLX backends are selected with OLLAMA_MLX_BACKENDS.

CUDA

Requires CUDA 13+ and cuDNN 9+.

shell
cmake -B build . -DOLLAMA_MLX_BACKENDS=cuda_v13
cmake --build build --parallel 8

Local MLX source overrides

To build against a local checkout of MLX and/or MLX-C (useful for development), set environment variables before running CMake:

shell
export OLLAMA_MLX_SOURCE=/path/to/mlx
export OLLAMA_MLX_C_SOURCE=/path/to/mlx-c

On macOS arm64:

shell
OLLAMA_MLX_SOURCE=../mlx OLLAMA_MLX_C_SOURCE=../mlx-c cmake -B build .
cmake --build build --parallel 8

For CUDA:

powershell
$env:OLLAMA_MLX_SOURCE="../mlx"
$env:OLLAMA_MLX_C_SOURCE="../mlx-c"
cmake -B build . -DOLLAMA_MLX_BACKENDS=cuda_v13
cmake --build build --parallel 8

Docker

shell
docker build .

ROCm

shell
docker build --build-arg FLAVOR=rocm .

Running tests

To run tests, use go test:

shell
go test ./...

Library detection

Ollama looks for native helper binaries and acceleration libraries in installed and local development layouts:

  • ../lib/ollama for standard installs where ollama is under bin/
  • ./lib/ollama for Windows release-style payloads and local dist output
  • . for macOS release artifacts that colocate helpers with ollama
  • build/lib/ollama and dist/<platform>/lib/ollama for local development builds

If the libraries are not found, Ollama will not run with any acceleration libraries.