mirror of
https://github.com/ggerganov/ggml
synced 2026-03-02 05:00:27 +01:00
0a6f36a11d
* model: add support for extra bufs for all devices * hexagon: add experimental ggml-hexagon backend for the Hexagon NPU This commit introduces a new experimental backend `ggml-hexagon` with support for the Hexagon NPU. Highlights: - Supports Hexagon versions: v73, v75, v79, and v81 - Targets Android devices based on Snapdragon SoCs: Gen3, 8-Elite, and 8-Elite Gen5 - Supports Q4_0, Q8_0, MXFP4, and FP32 data types - Implements core LLM ops: MUL_MAT/MUL_MAT_ID, ADD/SUB/MUL/ADD_ID, RMS_NORM, ROPE, GLU/SWIGLU, SOFTMAX **Note:** This backend is experimental and may exhibit instability or limited performance across supported devices. It is intended for early testing and feedback from llama.cpp/ggml developer and user community. Co-Authored-By: Rajdeep Ganguly <rganguly@qti.qualcomm.com> Co-Authored-By: Todor Boinovski <todorb@qti.qualcomm.com> * hexagon: fix format checker errors * hexagon: update readme and cmake presets * ci: add android-ndk-build jobs that build plain ARM64 and Snapdragon versions * hexagon: add simple graph optimizer for stacking MUL_MAT ops with the same input * hexagon: move ADB helper scripts into scripts/snapdragon/adb * hexagon: replace all f/printfs with GGML_LOG_... * readme: add hexagon to the list supported backends * hexagon: stack malmuts with quantized inputs only * hexagon: add TODO for fixing issues in hexagon_graph_optimize * hexagon: update to hex-sdk 6.4.0 and add scripts for running on QDC * scripts: fix lint errors * scripts: update qdc pytest script to make linter happy * hexagon: add reduce sum in fp32 * hexagon: reduce number of vector stores in matmul output * hexagon: remove the need for vdelta in reduce-multiply-x8 * hexagon: consistent use of reduce_sum_fp32 for row_sums * hexagon: some more matmul optimizations and comments Optimize cases where tensor dims are not multiple of 1024 (e.g in Qwen models). We've handled those cases already but at a higher overhead. * hexagon: update cmake presets * hexagon: add OPMASK support for run-bench.sh wrapper * hexagon: update to use GGML_BACKEND_API * hexagon: remove unused logic for setting tensor flags for the views * hexagon: add asserts to set/get_tensor to make sure we handle complete tensors Same asserts as the CPU backend. * hexagon: use cpy_tensor slow path for non-host buffers * hexagon: error checks in the buffer allocator * cmake: move include(extProj) under ggml-hexagon * hexagon: don't forget to delete the backend on free * hexagon: set/get_tensor size assert apply only to quantized tensors * hexagon: reintroduce HEX_VERBOSE wrapper for GGML_LOG_DEBUG for now GGML_LOG_DEBUG is always enabled for test-backend-ops and the output gets in the way. Ideally we need a bit more finer log levels. * docs: typos in hexagon developer docs (libggm-...) * hexagon: overhaul error handling in the session/device allocation this should handle all failure paths in the session allocation. * hexagon: update cmake presets to enable fp16 vectors * hexagon: remove unused time_usec function * hexagon: don't forget to release buffer contexts * hexagon: fixed indents in hvx-utils (missed clang-format auto-format failure) * hexagon: remove custom can_repeat function and use ggml_can_repeat --------- Co-authored-by: Rajdeep Ganguly <rganguly@qti.qualcomm.com> Co-authored-by: Todor Boinovski <todorb@qti.qualcomm.com> |
||
|---|---|---|
| .github | ||
| ci | ||
| cmake | ||
| docs | ||
| examples | ||
| include | ||
| scripts | ||
| src | ||
| tests | ||
| .editorconfig | ||
| .gitignore | ||
| .gitmodules | ||
| AUTHORS | ||
| CMakeLists.txt | ||
| CONTRIBUTING.md | ||
| ggml.pc.in | ||
| LICENSE | ||
| README.md | ||
| requirements.txt | ||
ggml
Tensor library for machine learning
Note that this project is under active development.
Some of the development is currently happening in the llama.cpp and whisper.cpp repos
Features
- Low-level cross-platform implementation
- Integer quantization support
- Broad hardware support
- Automatic differentiation
- ADAM and L-BFGS optimizers
- No third-party dependencies
- Zero memory allocations during runtime
Build
git clone https://github.com/ggml-org/ggml
cd ggml
# install python dependencies in a virtual environment
python3.10 -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt
# build the examples
mkdir build && cd build
cmake ..
cmake --build . --config Release -j 8
GPT inference (example)
# run the GPT-2 small 117M model
../examples/gpt-2/download-ggml-model.sh 117M
./bin/gpt-2-backend -m models/gpt-2-117M/ggml-model.bin -p "This is an example"
For more information, checkout the corresponding programs in the examples folder.
Using CUDA
# fix the path to point to your CUDA compiler
cmake -DGGML_CUDA=ON -DCMAKE_CUDA_COMPILER=/usr/local/cuda-12.1/bin/nvcc ..
Using hipBLAS
cmake -DCMAKE_C_COMPILER="$(hipconfig -l)/clang" -DCMAKE_CXX_COMPILER="$(hipconfig -l)/clang++" -DGGML_HIP=ON
Using SYCL
# linux
source /opt/intel/oneapi/setvars.sh
cmake -G "Ninja" -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx -DGGML_SYCL=ON ..
# windows
"C:\Program Files (x86)\Intel\oneAPI\setvars.bat"
cmake -G "Ninja" -DCMAKE_C_COMPILER=cl -DCMAKE_CXX_COMPILER=icx -DGGML_SYCL=ON ..
Compiling for Android
Download and unzip the NDK from this download page. Set the NDK_ROOT_PATH environment variable or provide the absolute path to the CMAKE_ANDROID_NDK in the command below.
cmake .. \
-DCMAKE_SYSTEM_NAME=Android \
-DCMAKE_SYSTEM_VERSION=33 \
-DCMAKE_ANDROID_ARCH_ABI=arm64-v8a \
-DCMAKE_ANDROID_NDK=$NDK_ROOT_PATH
-DCMAKE_ANDROID_STL_TYPE=c++_shared
# create directories
adb shell 'mkdir /data/local/tmp/bin'
adb shell 'mkdir /data/local/tmp/models'
# push the compiled binaries to the folder
adb push bin/* /data/local/tmp/bin/
# push the ggml library
adb push src/libggml.so /data/local/tmp/
# push model files
adb push models/gpt-2-117M/ggml-model.bin /data/local/tmp/models/
adb shell
cd /data/local/tmp
export LD_LIBRARY_PATH=/data/local/tmp
./bin/gpt-2-backend -m models/ggml-model.bin -p "this is an example"