• TensorFlow Lite for Microcontrollers
• Build Status
  • Official Builds
  • Community Supported Builds
• Contributing
• Getting Help
• Additional Documentation
• RFCs

TensorFlow Lite for Microcontrollers is a port of TensorFlow Lite designed to run machine learning models on DSPs, microcontrollers and other devices with limited memory.

Additional Links:

• Tensorflow github repository
• TFLM at tensorflow.org

• GitHub Status

Build Type	Status
CI (Linux)
Code Sync

Build Type	Status
Arduino
Cortex-M
ESP32
RISC-V
Sparkfun Edge
Xtensa

See our contribution documentation.

A Github issue should be the primary method of getting in touch with the TensorFlow Lite Micro (TFLM) team.

The following resources may also be useful:

1. SIG Micro email group and monthly meetings.

2. SIG Micro gitter chat room.

3. For questions that are not specific to inference with TFLM (for example model conversion and quantization) please use the following resources:

   • Send an email to the TfLite Mailing List
   • Create a TensorFlow Lite Converter Issue
   • Create an issue in the model optimization toolkit GitHub repository

• Continuous Integration
• Benchmarks
• Profiling
• Memory Management
• Optimized Kernel Implementations
• New Platform Support
• Software Emulation with Renode

1. Pre-allocated tensors
2. TensorFlow Lite for Microcontrollers Port of 16x8 Quantized Operators