Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[Docs] Add MLX backend #251

Merged
merged 2 commits into from
Sep 25, 2024
Merged

[Docs] Add MLX backend #251

merged 2 commits into from
Sep 25, 2024

Conversation

grorge123
Copy link
Contributor

Explanation

Add MLX install documentation.

Related issue

#3688

What type of PR is this

/kind documentation

Copy link
Member

juntao commented Sep 9, 2024

Hello, I am a PR summary agent on flows.network. Here are my reviews of code commits in this PR.


This change is not necessary as the dynamic library file name should be libwasmedgePluginWasiNN.so on Linux and libwasmedgePluginWasiNN.dylib on MacOS, regardless of the backend used.
2. Explains that MLX (Machine Learning eXtended Library) is a part of WebAssembly specification but it's not defined yet. However, it should be clarified that MLX is an open source library for running machine learning models inside WebAssembly.
3. Instructions to build WasmEdge with MLX as the backend are provided in the pull request. Developers need to follow these steps and compile WasmEdge with WASMEDGE_PLUGINS=wasmedgePlugin, MLX_PATH=<path-to-mlx> in order to link it dynamically at runtime.
4. It's important that users have the MLX library installed correctly for WASI-NN to work properly. The path of the MLX library (MLX_PATH) should match with where the MLX library is actually located on their system.

Details

Commit 30c44a0d23d60aadc71e9abffd613ed10cec54b4

The Pull Request titled "[Docs] Add MLX backend" is proposing to update the documentation of the WasmEdge project by adding instructions on how to build and install this project with the MLX backend for WASI-NN, a neural network API that provides support to execute machine learning models in WebAssembly. This change will allow users to use the MLX (a Machine Learning eXtended Library) as the backend for running machine learning operations inside WebAssembly.

Commit 4b6c7da48933bd93df4dfa0940745870b2c77549

:

  1. Changes the name of Mac dynamic library file from libwasmedgePluginWasiNN.so to libwasmedgePluginWasiNN.dylib in documentation.

docs/contribute/source/plugin/wasi_nn.md Outdated Show resolved Hide resolved
@hydai hydai merged commit 0ed52dd into WasmEdge:main Sep 25, 2024
6 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants