https://github.com/utakotoba/mlx-lattice

Sparse convolution library for MLX designed for point cloud operation.
https://github.com/utakotoba/mlx-lattice

inference mlx neural-network point-cloud sparse sparse-matrix training

Last synced: about 1 month ago
JSON representation

Sparse convolution library for MLX designed for point cloud operation.

• Host: GitHub
• URL: https://github.com/utakotoba/mlx-lattice
• Owner: utakotoba
• License: mit
• Created: 2026-05-28T10:52:25.000Z (about 2 months ago)
• Default Branch: main
• Last Pushed: 2026-06-08T13:33:34.000Z (about 1 month ago)
• Last Synced: 2026-06-08T15:25:54.126Z (about 1 month ago)
• Topics: inference, mlx, neural-network, point-cloud, sparse, sparse-matrix, training
• Language: C++
• Homepage: https://pypi.org/project/mlx-lattice/
• Size: 427 KB
• Stars: 4
• Watchers: 0
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE
  • Citation: CITATION.cff

Awesome Lists containing this project

README

          
### MLX Lattice

Sparse convolution library for Apple [MLX](https://github.com/ml-explore/mlx) designed for point cloud operations.

> [!WARNING]

> Current branch is mainly used for refactoring for version 0.2.0.

### Acknowledgement

This project is heavily based on [MLX](https://github.com/ml-explore/mlx), an array framework for machine learning on Apple silicon developed by Apple machine learning research.

### License

Copyright © 2026 Z.Y. Lin; open sourced under [MIT license](/LICENSE)

### Citation

If you use this project in research, please cite this repository using the metadata in [`CITATION.cff`](./CITATION.cff).

```BibTex

@software{mlx-lattice2026,

  author = {Lin, Zhenyan},

  license = {MIT},

  title = {{mlx-lattice}: Sparse convolution library for MLX},

  url = {https://github.com/utakotoba/mlx-lattice},

  year = {2026},

}

```

This project uses [MLX](https://github.com/ml-explore/mlx) for machine learning on Apple silicon. If MLX is relevant to your research results, please cite MLX as requested by its authors, refer to [mlx#citing-mlx](https://github.com/ml-explore/mlx#citing-mlx).