5. Installing the Compiler

Note

The typical use model for the compiler is to invoke it from within EdgeAI Studio or Tiny ML ModelMaker.

5.1. Installing

TI Neural Network Compiler for MCUs is distributed as a prebuilt Python package in wheel format. It can be installed using a standard Python wheel installation mechanism. For example:

pip3 install ./ti_mcu_nnc-1.2.0-cp310-cp310-linux_x86_64.whl

5.2. Verifying install

After installation, verify that the compiler is available as follows:

which tvmc
python3 -c "import tvm; print(tvm.__file__)"
ls `python3 -c "import tvm; print(tvm.__path__[0])"`/ti_docs/index.html