zhangyiss/mlx
1
0
Fork 0
mirror of https://github.com/ml-explore/mlx.git synced 2025-10-31 16:21:27 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

No CPU option for binary minimization (#1105)

Browse Source 
* no cpu build option

* docs

* fix
This commit is contained in:
Awni Hannun
2024-05-13 16:08:11 -07:00
committed by GitHub
parent e7f9710499
commit 7178ac0111
11 changed files with 557 additions and 401 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
docs/src/install.rst
View File

@@ -153,6 +153,8 @@ should point to the path to the built metal library.
- OFF
* - MLX_BUILD_METAL
- ON
* - MLX_BUILD_CPU
- ON
* - MLX_BUILD_PYTHON_BINDINGS
- OFF
* - MLX_METAL_DEBUG
@@ -179,10 +181,28 @@ should point to the path to the built metal library.
xcrun -sdk macosx --show-sdk-version
Binary Size Minimization
~~~~~~~~~~~~~~~~~~~~~~~~
To produce a smaller binary use the CMake flags `CMAKE_BUILD_TYPE=MinSizeRel`
and `BUILD_SHARED_LIBS=ON`.
The MLX CMake build has several additional options to make smaller binaries.
For example, if you don't need the CPU backend or support for safetensors and
GGUF, you can do:
```shell
cmake .. \
-DCMAKE_BUILD_TYPE=MinSizeRel \
-DBUILD_SHARED_LIBS=ON \
-DMLX_BUILD_CPU=ON \
-DMLX_BUILD_SAFETENSORS=OFF \
-DMLX_BUILD_GGUF=OFF
```
Troubleshooting
^^^^^^^^^^^^^^^
Metal not found
~~~~~~~~~~~~~~~