Python bindings for ggml
Python bindings for the ggml
tensor library for machine learning.
⚠️ This project is in a very early state and currently only offers the basic low-level bindings to ggml
You can install ggml-python
using pip
:
pip install ggml-python
This will compile ggml using cmake which requires a c compiler installed on your system.
To build ggml with specific features (ie. OpenBLAS, GPU Support, etc) you can pass specific flags through the CMAKE_ARGS
environment variable. For example to install ggml-python with cuBLAS support you can run:
CMAKE_ARGS="-DGGML_CUBLAS=ON" pip install ggml-python
Option | Description | Default |
---|---|---|
GGML_CUBLAS |
Enable cuBLAS support | OFF |
GGML_CLBLAST |
Enable CLBlast support | OFF |
GGML_OPENBLAS |
Enable OpenBLAS support | OFF |
If you are having trouble installing ggml-python
or activating specific features please try to install it with the --verbose
and --no-cache-dir
flags to get more information about any issues:
[options] pip install ggml-python --verbose --no-cache-dir --force-reinstall --upgrade
This project is licensed under the terms of the MIT license.