Simplicity Machine Learning Version 1.2.0-beta Release Notes (Oct 14, 2026)#

The Artificial Intelligence and Machine Learning (AI/ML) tools include Simplicity Machine Learning, the model graph viewer, and the model converter. Use these tools to prepare, convert, quantize, and profile models on the host system.

Release Summary#

Key Features | Bug Fixes | Chip Enablement

Key Features#

Added in 1.2.0-beta#

• Added model quantization, including full integer (INT8) quantization using calibration data.

• Added the sml-compile CLI and sml.compile() Python API for compiling TFLite models.

• Added Ultralytics YOLO model support to the ML Model Converter.

Added in 1.1.0#

• The "ML Profiler" tool was renamed to "Simplicity Machine Learning".

• Added an option to choose kernels when profiling a model.

• Improved central processing unit (CPU) and accelerator cycle counts in the profiler.

• Added a model graph viewer to Simplicity Machine Learning based on Model Explorer.

• Added an alpha release of the ML Model Converter to convert PyTorch and Open Neural Network Exchange (ONNX) models to TensorFlow Lite (TFLite).

Bug Fixes#

Fixed in 1.2.0-beta#

• Fixed a Windows issue when resolving the Silicon Labs Device Manager executable.

• Fixed missing Ultralytics and PyTorch dependencies in the packaged model converter.

• Added a clear error message when the model selected for profiling is not in TFLite format.

Fixed in 1.1.0#

None.

Chip Enablement#

None.

Key Features#

New Features | Enhancements | Removed Features | Deprecated Features

Note: See Feature Matrix for a list of any applicable application programming interfaces (APIs), examples, software variants, modes, hardware, and host interfaces for each feature.

New Features#

Added in 1.2.0-beta#

• Model quantization: Added quantization support to model conversion, including full INT8 quantization using calibration data. Calibration files can be selected from the GUI or provided through the CLI.

• Dynamic INT8 conversion: Added an ONNX fallback path for dynamic INT8 conversion of PyTorch models.

• ML Model Compiler: Added the sml-compile CLI and sml.compile() Python API for compiling TFLite models.

Added in 1.1.0#

• Simplicity Machine Learning profiler: Renamed from "ML Profiler" to "Simplicity Machine Learning". This host-side tool profiles ML models on target hardware.

• Kernel selection: Added an option to choose kernels when profiling a model.

• Model graph viewer: Integrated a model graph viewer in Simplicity Machine Learning based on Model Explorer. Linux and macOS are supported natively; Windows is supported through Windows Subsystem for Linux (WSL).

• ML Model Converter: Added a unified graphical user interface (GUI) and command-line interface (CLI) to convert PyTorch and ONNX models to TFLite.

• manifest.json output: When --save-manifest command line argument is passed on the CLI, a manifest.json file is saved with conversion metadata including conversion time, conversion ratio, input shape, and output shape. The GUI generates this file every time.

Enhancements#

Added in 1.2.0-beta#

• Unified conversion command: Updated the umbrella sml CLI to invoke sml-convert directly for model conversion.

• Compiler output: Simplified the sml-compile CLI to always stage the compiled model and emit a model header.

• Compiler workspace cleanup: Restored the clean-workspace CLI option in the sml-compileCLI.

• Profiling output: Updated the profiler output directory structure.

• Profiling firmware: Updated Simplicity Machine Learning to use profiling firmware version 1.1.2.

• Model file handling: Standardized support for .tflite, .pt, .pth, and .onnx model extensions across the GUI and CLI.

Added in 1.1.0#

• Profiler metrics: Improved CPU and accelerator cycle count reporting in Simplicity Machine Learning.

Removed Features#

Removed in 1.2.0-beta#

None.

Removed in 1.1.0#

None.

Deprecated Features#

Deprecated in 1.1.0#

The "ML Profiler" tool will not receive any updates. In Simplicity Studio, search for Simplicity Machine Learning (GUI) or Simplicity Machine Learning (CLI).

Bug Fixes#

Fixed in 1.2.0-beta#

• Fixed a Windows issue by resolving the Silicon Labs Device Manager executable as sdm or sdm.exe, depending on the host operating system.

• Fixed missing Ultralytics and PyTorch dependencies in the packaged model converter.

• Added a clear error message when a model selected for profiling is not a .tflite file.

Fixed in 1.1.0#

None.

Chip Enablement#

None.

Known Issues and Limitations#

Refer to the ML Profiler Troubleshooting section for known issues and their solutions.

Refer to the ML Model Converter Troubleshooting section for known issues and their solutions.

• The model graph viewer is not supported natively on Windows; use WSL to launch the GUI tool.

• The model converter is not supported natively on Windows; use WSL to launch the GUI tool.

  • ONNX models are converted using onnx2tf. Non-self-contained ONNX models with external weights are rejected with a clear message

  • PyTorch models with dynamic graphs require an explicit input shape input.

  • Full INT8 quantization requires representative calibration data. Provide representative calibration data when using full INT8 quantization.

Installation and Use#

Refer to the Getting Started guide for installation and usage instructions.

For information about Secure Vault Integration, see Secure Vault.

Help and Feedback#

• Contact Silicon Labs Support.

• To use the Ask AI tool, see the search field at the top of this page.

• Get help from our developer community.

Feature Matrix#

Supported Features | Unsupported Features

Supported Features#

Unsupported Features#

• The model graph viewer is not supported natively on Windows. Use WSL to launch the GUI tool.

• The model converter is not supported natively on Windows. Use WSL to launch the GUI tool.

SDK Release and Maintenance Policy#

See our SDK Release and Maintenance Policy.