Silicon Labs AI/ML Version 3.0.0 - Release Notes (Jun 23, 2026)#

Simplicity SDK Version 2026.6.0

The Silicon Labs AI/ML SDK enables machine learning development on Series 2 (EFR and SiWG917) devices using the Tensorflow Lite for Microcontrollers (TFLM) framework.

Release Summary#

Release Item	Version	Release Date	Release Notes	Key Features	API Changes	Bug Fixes	Chip Enablement
AI/ML SDK	3.0.0	Jun 23, 2026	Release Notes	New DX for adding ML Models to new or existing projects. New APIs to initialize, execute, and de-initialize ML models. Project upgrades require manual effort. See the AI-assisted migration prompt. New optimizations to enable faster inference with `.tflite` models. Model code generation now triggers on `.mlconf` files instead of `.tflite` files. Multiple-Model feature to add and execute multiple ML models in a project.	New: `sl_ml_model_init()`, `sl_ml_model_run()`, and `sl_ml_model_deinit()` APIs support adding Multiple Models. Deprecated: Legacy model-specific APIs and TFLite Micro init/tensor APIs for application use. Changed: Use `ml_model` as the starter component instead of adding `tensorflow_lite_micro` directly.	Fixed microphone integration on SiWG917 (BRD2605A) using ULP_I2S interface.	Added support for EFM32 devices.
MVP Math Library	6.0.0	Jun 23, 2026	Release Notes	MVP Math Library release notes moved from Platform to AI/ML. NN kernels moved from MVP Math Library to AI/ML SDK. Renamed "MVP Math Demo" sample application to "Compute - SoC Math MVP EFR32".	None.	None.	None.

Impact of Release Changes#

Impact Statements | Migration Guide

Impact Statements#

Breaking changes in this release require project migration. See the AI/ML 3.0 Migration Guide for step-by-step instructions.

Change	Impact	Affected Software Variants if applicable	Affected Modes	Affected OPNs / Boards / OPN Combinations	Affected Host Interfaces
New `ml_model` component and `.mlconf` workflow	Existing projects cannot be upgraded automatically. Manual migration is required. Use `ml_model` as the starter component instead of adding `tensorflow_lite_micro` directly. The `ml_model` component requires `tensorflow_lite_micro`, which is not removed and brings in the generic model APIs. Model code generation now triggers on `.mlconf` files instead of `.tflite` files. Use the AI-assisted migration prompt to help migrate existing projects.	Standard	SoC	EFR32, SiWG917, EFM32	None.
New `sl_ml_model_*` runtime APIs	Replace per-model init/run APIs and TFLite Micro Interpreter based execution with `sl_ml_model_init()`, `sl_ml_model_run()`, and `sl_ml_model_deinit()`. Use instance-based handles (`sl_ml_<model>_model_handle`) instead of legacy per-model globals and `sl_tflite_micro_*` APIs. See Deprecated APIs in the AI/ML SDK release notes for the full migration map.	Standard	SoC	EFR32, SiWG917, EFM32	None.
GCC 14.2 Rel1	GCC updated from 12.2.1 to 14.2 Rel1. On Windows and macOS (Apple Silicon), use the Silicon Labs-provided GCC 14.2 Rel1 toolchain to build with LTO-enabled SDK libraries. Using the ARM-released GCC toolchain on these platforms with LTO enabled may result in link-time errors.	None.	None.	EFR32, SiWG917, EFM32	None.
IAR 9.70.3 (EFR32 only)	IAR 9.70.3 is supported on EFR32 devices only. SiWG917 IAR support is not available yet. Rebuild all EFR32 projects after upgrading the toolchain.	Standard	SoC	EFR32	None.
NN kernels moved to AI/ML SDK	Neural network kernels previously provided by the MVP Math Library are now part of the AI/ML SDK. Applications that used NN kernels from the MVP Math Library should use AI/ML SDK components instead.	Standard	SoC	EFR32xG24, EFR32xG26, EFR32xG28, SiWG917	None.

Migration Guide#

Click here for the migration guide for deprecated, removed, and modified items.

Using This Release#

What's in the Release? | Compatible Software | Installation and Use | Help and Feedback

What's in the Release?#

This release includes:

AI/ML SDK 3.0.0 — On-device ML runtime, Multiple-Model support, new model APIs, sample applications, and compiler upgrades.
MVP Math Library 6.0.0 — Matrix and vector operations using the Matrix Vector Processor, now delivered as part of the AI/ML SDK.

Compatible Software#

Software	Compatible Version or Variant
Software Development Kit (SDK)	Simplicity SDK: 2026.6.0 WiSeConnect SDK: 4.1.0

Installation and Use#

To upgrade your existing software with the latest features included in this release, update Simplicity Studio to the latest version, Simplicity SDK to v2026.6.0, WiSeConnect SDK to v4.1.0, and AI/ML SDK to v3.0.0 using Studio installation manager. Alternatively, download the SDKs from the links listed in the Compatible Software section above.

To run your first demo, see our Getting Started

To kick start your development, see our Developer's Guide For information about Secure Vault Integration, see Secure Vault.

To review Security and Software Advisory notifications and manage your notification preferences:

Go to https://community.silabs.com/.
Log in with your account credentials.
Click your profile icon in the upper-right corner of the page.
Select Notifications from the dropdown menu.
In the Notifications section, go to the My Product Notifications tab to review historical Security and Software Advisory notifications.
To manage your preferences, use the Manage Notifications tab to customize which product updates and advisories you receive.

To learn more about the software in this release, dive into our online documentation

Help and Feedback#

Contact Silicon Labs Support.
To use our Ask AI tool to get answers, see the search field at the top of this page.
Note: Ask AI is experimental.
Get help from our developer community.

Feature Matrix#

Supported Features | Unsupported Features

See the detailed feature matrix in each component release notes page:

Supported Features#

Feature Name	Description	Quality	Related API Names	Supported Software Variants, Hardware, Modes, Host Interfaces	Related Example Names
ML model runtime APIs	Initialize, execute, and de-initialize ML models using instance-based handles.	Alpha	sl_ml_model_init() sl_ml_model_run() sl_ml_model_deinit()	Standard EFR32/EFM32, SiWG917 SoC	AI/ML sample and demo applications
Multiple-Model	Add and execute multiple ML models in a single project.	Alpha	sl_ml_model_init() sl_ml_model_run() sl_ml_model_deinit()	Standard EFR32, SiWG917 SoC	AI/ML - SoC Voice Control Light + Sine Blink concurrent MicriumOS EFR32 AI/ML - SoC Voice Control Light + Sine Blink sequential MicriumOS EFR32 AI/ML - SoC Voice Control Light + Sine Blink concurrent SiWG917 AI/ML - SoC Voice Control Light + Sine Blink sequential SiWG917
`ml_model` component and `.mlconf` workflow	New starter component for adding ML models to projects. The `ml_model` component requires `tensorflow_lite_micro`, which is not removed and provides the underlying TFLM runtime and generic model APIs. Model code generation triggers on `.mlconf` files. Projects cannot be upgraded automatically and require manual migration.	Alpha	ml_model component	Standard EFR32, SiWG917 SoC	AI/ML sample and demo applications
Model optimization	Software optimizations for faster inference with `.tflite` models.	Alpha	Model optimization	Standard SiWG917 SoC	AI/ML sample and demo applications for SiWG917
MVP Math Library	Real and complex matrix and vector operations using the Matrix Vector Processor on supported EFR32 and SiWG917 devices. Alternative to CMSIS-DSP for matrix and vector math operations.	Production	MVP Math Library	Standard EFR32xG24, EFR32xG26, EFR32xG28, SiWG917 SoC	Compute - SoC Math MVP EFR32
Wi-Fi + ML applications	Sample applications combining Wi-Fi connectivity and on-device ML inference on SiWG917.	Experimental	ML model runtime APIs	Standard SiWG917 (requires WiSeConnect SDK 4.1.0) SoC	Voice Controlled Light over Wi-Fi `aiml_wifi_voice_control_light_siwg917_freertos_soc` `aiml_wifi_switch_led_siwg917_freertos_soc`

Unsupported Features#

IAR 9.70.3 is supported on EFR32 devices only; SiWG917 IAR support is not available yet.
Series 2 devices do not support new software optimizations for inference; due to their architecture, they remain at least as efficient as SiWG917.
NN kernels are no longer provided by the MVP Math Library. Use AI/ML SDK components for neural network kernel operations.

SDK Release and Maintenance Policy#

See our SDK Release and Maintenance Policy.