|
1 | 1 | # Python bindings for [`ggml`](https://github.com/ggerganov/ggml) |
2 | 2 |
|
3 | | -[](https://ggml-python.readthedocs.io/en/latest/?badge=latest) |
4 | | -[](https://github.com/abetlen/ggml-python/actions/workflows/test.yaml) |
5 | | -[](https://pypi.org/project/ggml-python/) |
6 | | -[](https://pypi.org/project/ggml-python/) |
7 | | -[](https://pypi.org/project/ggml-python/) |
8 | | -[](https://pypi.org/project/ggml-python/) |
| 3 | +[](https://pypi.org/project/ggml-py/) |
| 4 | +[](https://pypi.org/project/ggml-py/) |
| 5 | +[](https://pypi.org/project/ggml-py/) |
| 6 | +[](https://pypi.org/project/ggml-py/) |
9 | 7 |
|
| 8 | +> ℹ️ Note this is a fork of the [original project](https://github.com/abetlen/ggml-python) which hasn't been updated July 2024. There have been a number of CVE security patches for `ggml / llama.cpp` since that date. This fork updates `ggml` to the latest. [See the llama.cpp security page for more on this](https://github.com/ggml-org/llama.cpp/security). |
10 | 9 |
|
11 | 10 | Python bindings for the [`ggml`](https://github.com/ggerganov/ggml) tensor library for machine learning. |
12 | 11 |
|
13 | | -> ⚠️ Neither this project nor `ggml` currently guarantee backwards-compatibility, if you are using this library in other applications I strongly recommend pinning to specific releases in your `requirements.txt` file. |
14 | | -
|
15 | | -# Documentation |
16 | | - |
17 | | -- [Getting Started](https://ggml-python.readthedocs.io/en/latest/) |
18 | | -- [API Reference](https://ggml-python.readthedocs.io/en/latest/api-reference/) |
19 | | -- [Examples](https://github.com/abetlen/ggml-python/tree/main/examples) |
20 | | - |
21 | 12 | # Installation |
22 | 13 |
|
23 | | - |
24 | 14 | Requirements |
25 | | -- Python 3.8+ |
| 15 | +- Python 3.10+ |
26 | 16 | - C compiler (gcc, clang, msvc, etc) |
27 | 17 |
|
28 | | -You can install `ggml-python` using `pip`: |
| 18 | +You can install `ggml-py` using `pip`: |
29 | 19 |
|
30 | 20 | ```bash |
31 | | -pip install ggml-python |
| 21 | +pip install ggml-py |
32 | 22 | ``` |
33 | 23 |
|
34 | 24 | This will compile ggml using cmake which requires a c compiler installed on your system. |
35 | | -To build ggml with specific features (ie. OpenBLAS, GPU Support, etc) you can pass specific cmake options through the `cmake.args` pip install configuration setting. For example to install ggml-python with cuBLAS support you can run: |
| 25 | +To build ggml with specific features (ie. OpenBLAS, GPU Support, etc) you can pass specific cmake options through the `cmake.args` pip install configuration setting. For example to install ggml-py with cuBLAS support you can run: |
36 | 26 |
|
37 | 27 | ```bash |
38 | 28 | pip install --upgrade pip |
39 | | -pip install ggml-python --config-settings=cmake.args='-DGGML_CUDA=ON' |
| 29 | +pip install ggml-py --config-settings=cmake.args='-DGGML_CUDA=ON' |
40 | 30 | ``` |
41 | 31 |
|
42 | 32 | ## Options |
@@ -89,10 +79,10 @@ ggml.ggml_free(ctx) |
89 | 79 |
|
90 | 80 | # Troubleshooting |
91 | 81 |
|
92 | | -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: |
| 82 | +If you are having trouble installing `ggml-py` or activating specific features please try to install it with the `--verbose` and `--no-cache-dir` flags to get more information about any issues: |
93 | 83 |
|
94 | 84 | ```bash |
95 | | -pip install ggml-python --verbose --no-cache-dir --force-reinstall --upgrade |
| 85 | +pip install ggml-py --verbose --no-cache-dir --force-reinstall --upgrade |
96 | 86 | ``` |
97 | 87 |
|
98 | 88 | # License |
|
0 commit comments