Release Notes
Changelog
ZETIC Melange SDK release notes and version history.
This page tracks release notes and version history for the ZETIC Melange SDK and platform.
Flutter 1.11.1 / Android and iOS 1.11.0
zetic_mlange 1.11.1 pins both its Android and iOS native SDK dependencies to 1.11.0. Use this Flutter package version when integrating the native 1.11.0 release; Flutter 1.11.0 has been retracted.
Install
| Platform | Install |
|---|---|
| Android | implementation("com.zeticai.mlange:mlange:1.11.0") (Gradle Ivy setup) |
| iOS | https://github.com/zetic-ai/ZeticMLangeiOS at 1.11.0 |
| Flutter | zetic_mlange: ^1.11.1 |
1.9.1
ZeticMLange Flutter 1.9.1 aligns the RAG API with Android and iOS by moving RAG generation to RagPipeline.
What Changed
- Added Flutter
RagPipelineas the public RAG generation entry point. - Removed model-level Flutter RAG helper methods from
ZeticMLangeLLMModel. - Updated Flutter RAG documentation and examples to the composition-based API.
Install
| Platform | Install |
|---|---|
| Flutter | zetic_mlange: ^1.9.1 |
1.9.0
ZeticMLange 1.9.0 expands on-device AI across Android, iOS, and Flutter with vision-language support, function calling, RAG, and stronger runtime reliability.
What Changed
- LFM-VL support for local image + text vision-language models on Android, iOS, and Flutter.
- Function calling APIs for connecting model output to app-defined tools.
- RAG APIs for retrieval and context-grounded generation workflows.
- KV state persistence on native Android and iOS for save, load, and reset flows.
- More reliable model loading and inference through backend selection caching, lifecycle cleanup, native handle ownership, and Flutter image-copy improvements.
Install
| Platform | Install |
|---|---|
| Android | implementation("com.zeticai.mlange:mlange:1.9.0") |
| iOS | https://github.com/zetic-ai/ZeticMLangeiOS at 1.9.0 |
| Flutter | zetic_mlange: ^1.9.0 |
Earlier 2025 Updates
LLM Inference Engine
- Added support for
google/gemma-3-4b-it. - Added support for
LiquidAI/LFM2.5-1.2B-Instruct. - KV cache cleanup policy configuration with
LLMKVCacheCleanupPolicy. - Download progress callback support.
- Speed inference mode with
LLMModelMode.RUN_SPEED.
Hugging Face Integration
ZeticMLangeHFModelfor loading models directly from Hugging Face.- Automatic download, compilation, and caching.
General SDK
- PyTorch Exported Program (
.pt2) support. - Inference mode selection with
RUN_AUTO,RUN_SPEED, andRUN_ACCURACY. - Performance-adaptive deployment across real devices.
- Docs site migration to
docs.zetic.ai.
For the latest updates and announcements, follow us on GitHub and join our Discord community.
SDK Repositories
| Platform | Repository | Install |
|---|---|---|
| Android | ZeticMLangeAndroid GitHub release | implementation("com.zeticai.mlange:mlange:1.11.0") (Gradle Ivy setup) |
| iOS | ZeticMLangeiOS | Swift Package Manager 1.11.0 |
| Flutter | pub.dev | zetic_mlange: ^1.11.1 (Android apps also need the Gradle Ivy setup) |