ZETIC.MLange API

ZETIC.MLange API#

MLange icon image

ZETIC.MLange is an On-device AI runtime library supporting heterogeneous Mobile NPUs’ utilizations.

We provide the real On-device AI immediately with key features below
  1. End-to-end on-device AI

  2. One-stop deployment

  3. Heterogeneous OS and target Hardware supporting

In this documentations, we provide instructions and examples for the ZETIC.MLange. Since we are keep developing very hardly with speed, Please contact ZETIC.ai for any kind of issues.

This is the `Beta` version of the ZETIC.MLange before official release.


Quick Start#

  1. Get mlange_gen to generate ZETIC.MLange

$ wget https://github.com/zetic-ai/ZETIC_MLange_document/raw/main/bin/mlange_gen
  1. Let ZETIC.MLange automatically make runnable target model for heterogeneous target devices!

$ ./mlange_gen -m ai_model -i input0.npy,input1.npy,...

# ...
# MLange Model Key : {YOUR_MODEL_KEY}
  1. Use your model key in Mobile Applications

  • Android - Kotlin

val model = ZeticMLangeModel(this, "YOUR MODEL KEY")
model.run(YOUR_INPUT_BYTE_BUFFERS)
  • iOS - Swift

let model = try ZeticMLangeModel("YOUR MODEL KEY")
model.run(YOUR_INPUT_DATA_ARRAY)

Contents#

Additional features

Index | Search Page