- Background
- OS
- Hardware
- DataType Supports
- Model Preparation
- CMake Options
- Android
- Windows 11 Arm64
- Known Issue
- TODO
OpenCL (Open Computing Language) is an open, royalty-free standard for cross-platform, parallel programming of diverse accelerators found in supercomputers, cloud servers, personal computers, mobile devices and embedded platforms. OpenCL specifies a programming language (based on C99) for programming these devices and application programming interfaces (APIs) to control the platform and execute programs on the compute devices. Similar to CUDA, OpenCL has been widely used to program GPUs and is supported by most GPU vendors.
The llama.cpp OpenCL backend is designed to enable llama.cpp on Qualcomm Adreno GPU firstly via OpenCL. Thanks to the portabilty of OpenCL, the OpenCL backend can also run on certain Intel GPUs although the performance is not optimal.
OS | Status | Verified |
---|---|---|
Android | Support | Snapdragon 8 Gen 3, Snapdragon 8 Elite |
Windows | Support | Windows 11 Arm64 with Snapdragon X Elite |
Linux | Support | Ubuntu 22.04 WSL2 with Intel 12700H |
Verified devices
Adreno GPU | Status |
---|---|
Adreno 750 (Snapdragon 8 Gen 3) | Support |
Adreno 830 (Snapdragon 8 Elite) | Support |
Adreno X85 (Snapdragon X Elite) | Support |
DataType | Status |
---|---|
Q4_0 | Support |
Q6_K | Support, but not optimized |
You can refer to the general Prepare and Quantize guide for model prepration.
Currently we support Q4_0
quantization and have optimize for it. To achieve best performance on Adreno GPU, add --pure
to llama-quantize
. For example,
./llama-quantize --pure ggml-model-qwen2.5-3b-f16.gguf ggml-model-qwen-3b-Q4_0.gguf Q4_0
Since Q6_K
is also supported, Q4_0
quantization without --pure
will also work. However, the performance will be worse compared to pure Q4_0
quantization.
The OpenCL backend has the following CMake options that control the behavior of the backend.
CMake options | Default value | Description |
---|---|---|
GGML_OPENCL_EMBED_KERNELS |
ON |
Embed OpenCL kernels into the executable. |
GGML_OPENCL_USE_ADRENO_KERNELS |
ON |
Use kernels optimized for Adreno. |
Ubuntu 22.04 is used for targeting Android. Make sure the following tools are accessible from command line,
- Git
- CMake 3.29
- Ninja
- Python3
- Install NDK
cd ~
wget https://dl.google.com/android/repository/commandlinetools-linux-8512546_latest.zip && \
unzip commandlinetools-linux-8512546_latest.zip && \
mkdir -p ~/android-sdk/cmdline-tools && \
mv cmdline-tools latest && \
mv latest ~/android-sdk/cmdline-tools/ && \
rm -rf commandlinetools-linux-8512546_latest.zip
yes | ~/android-sdk/cmdline-tools/latest/bin/sdkmanager "ndk;26.3.11579264"
- Install OpenCL Headers and Library
mkdir -p ~/dev/llm
cd ~/dev/llm
git clone https://github.com/KhronosGroup/OpenCL-Headers && \
cd OpenCL-Headers && \
cp -r CL ~/android-sdk/ndk/26.3.11579264/toolchains/llvm/prebuilt/linux-x86_64/sysroot/usr/include
cd ~/dev/llm
git clone https://github.com/KhronosGroup/OpenCL-ICD-Loader && \
cd OpenCL-ICD-Loader && \
mkdir build_ndk26 && cd build_ndk26 && \
cmake .. -G Ninja -DCMAKE_BUILD_TYPE=Release \
-DCMAKE_TOOLCHAIN_FILE=$HOME/android-sdk/ndk/26.3.11579264/build/cmake/android.toolchain.cmake \
-DOPENCL_ICD_LOADER_HEADERS_DIR=$HOME/android-sdk/ndk/26.3.11579264/toolchains/llvm/prebuilt/linux-x86_64/sysroot/usr/include \
-DANDROID_ABI=arm64-v8a \
-DANDROID_PLATFORM=24 \
-DANDROID_STL=c++_shared && \
ninja && \
cp libOpenCL.so ~/android-sdk/ndk/26.3.11579264/toolchains/llvm/prebuilt/linux-x86_64/sysroot/usr/lib/aarch64-linux-android
cd ~/dev/llm
git clone https://github.com/ggml-org/llama.cpp && \
cd llama.cpp && \
mkdir build-android && cd build-android
cmake .. -G Ninja \
-DCMAKE_TOOLCHAIN_FILE=$HOME/android-sdk/ndk/26.3.11579264/build/cmake/android.toolchain.cmake \
-DANDROID_ABI=arm64-v8a \
-DANDROID_PLATFORM=android-28 \
-DBUILD_SHARED_LIBS=OFF \
-DGGML_OPENCL=ON
ninja
A Snapdragon X Elite device with Windows 11 Arm64 is used. Make sure the following tools are accessible from command line,
- Git
- CMake 3.29
- Clang 19
- Ninja
- Visual Studio 2022
Powershell is used for the following instructions.
- Install OpenCL Headers and Library
mkdir -p ~/dev/llm
cd ~/dev/llm
git clone https://github.com/KhronosGroup/OpenCL-Headers && cd OpenCL-Headers
mkdir build && cd build
cmake .. -G Ninja `
-DBUILD_TESTING=OFF `
-DOPENCL_HEADERS_BUILD_TESTING=OFF `
-DOPENCL_HEADERS_BUILD_CXX_TESTS=OFF `
-DCMAKE_INSTALL_PREFIX="$HOME/dev/llm/opencl"
cmake --build . --target install
cd ~/dev/llm
git clone https://github.com/KhronosGroup/OpenCL-ICD-Loader && cd OpenCL-ICD-Loader
mkdir build && cd build
cmake .. -G Ninja `
-DCMAKE_BUILD_TYPE=Release `
-DCMAKE_PREFIX_PATH="$HOME/dev/llm/opencl" `
-DCMAKE_INSTALL_PREFIX="$HOME/dev/llm/opencl"
cmake --build . --target install
mkdir -p ~/dev/llm
cd ~/dev/llm
git clone https://github.com/ggml-org/llama.cpp && cd llama.cpp
mkdir build && cd build
cmake .. -G Ninja `
-DCMAKE_TOOLCHAIN_FILE="$HOME/dev/llm/llama.cpp/cmake/arm64-windows-llvm.cmake" `
-DCMAKE_BUILD_TYPE=Release `
-DCMAKE_PREFIX_PATH="$HOME/dev/llm/opencl" `
-DBUILD_SHARED_LIBS=OFF `
-DGGML_OPENCL=ON
ninja
- Qwen2.5 0.5B model produces gibberish output with Adreno kernels.
- Fix Qwen2.5 0.5B
- Optimization for Q6_K
- Support and optimization for Q4_K