Skip to main content

MLX-native computer vision for Apple Silicon: object detection, segmentation, and open-vocabulary grounding.

Project description

mlx-cv

MLX-native computer vision for Apple Silicon — object detection, segmentation, and open-vocabulary grounding.

PyPI Python License: MIT

⚠️ Pre-alpha / placeholder. This release reserves the package name. The public API is not yet defined and will change without notice.

What is this?

mlx-cv aims to be the detection & segmentation layer for the MLX ecosystem — sitting alongside mlx-lm and mlx-vlm, but focused on computer-vision tasks that run natively and efficiently on Apple Silicon.

Planned model support

  • SAM 3 — promptable segmentation
  • LocateAnything — open-vocabulary detection / localization
  • …and more detection / grounding architectures over time

Installation

pip install mlx-cv

Requires Python 3.9+ and an Apple Silicon Mac (for the eventual MLX runtime).

Status

Stage Status
Name reserved on PyPI
Public API 🚧 in design
First model port 🚧 planned

License

MIT © AppAutomaton

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

mlx_cv-0.0.1.tar.gz (3.2 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

mlx_cv-0.0.1-py3-none-any.whl (3.1 kB view details)

Uploaded Python 3

File details

Details for the file mlx_cv-0.0.1.tar.gz.

File metadata

  • Download URL: mlx_cv-0.0.1.tar.gz
  • Upload date:
  • Size: 3.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for mlx_cv-0.0.1.tar.gz
Algorithm Hash digest
SHA256 bc740284266f9fed0e664475c8d1f5f12e737192d312a6210d58a496f02b684e
MD5 b5bc4d1486d39c160f083960bb494115
BLAKE2b-256 2edb845c1ad1625e9ba2741230afc4997bc33910c6956982267bb0e59181c171

See more details on using hashes here.

Provenance

The following attestation bundles were made for mlx_cv-0.0.1.tar.gz:

Publisher: workflow.yml on appautomaton/mlx-cv

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file mlx_cv-0.0.1-py3-none-any.whl.

File metadata

  • Download URL: mlx_cv-0.0.1-py3-none-any.whl
  • Upload date:
  • Size: 3.1 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for mlx_cv-0.0.1-py3-none-any.whl
Algorithm Hash digest
SHA256 d8314894a3724e11311ada0dcf616602ba49665787e5c8ee8c1ccb7d8f2d3b07
MD5 26a0c7b89783ae56d0e3e6696426307d
BLAKE2b-256 703f3a838ed6dc3e6a439181bd447071585809b1b47755dfde8f30c33839ed97

See more details on using hashes here.

Provenance

The following attestation bundles were made for mlx_cv-0.0.1-py3-none-any.whl:

Publisher: workflow.yml on appautomaton/mlx-cv

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page