gromero opened a new pull request #9229: URL: https://github.com/apache/tvm/pull/9229
This patchset adds a new micro context to TVMC under `tvmc micro` command, allowing `tvmc` to be used for compiling, build, flashing, and running models on microTVM target devices. The following typical workflow is provided as an example: ```bash $ wget https://github.com/tensorflow/tflite-micro/raw/main/tensorflow/lite/micro/examples/micro_speech/micro_speech.tflite $ tvmc compile ./micro_speech.tflite --target="c -keys=cpu -link-params=0 -march=armv7e-m -mcpu=cortex-m7 -model=stm32f746xx -runtime=c -system-lib=1" --output micro_speech.tar --output-format mlf --pass-config tir.disable_vectorize=1 --disabled-pass="AlterOpLayout" $ tvmc micro create-project /tmp/micro_speech ./micro_speech.tar zephyr -o project_type=host_driven zephyr_board=stm32f746g_disco $ tvmc micro build /tmp/micro_speech zephyr -o zephyr_board=stm32f746g_disco $ tvmc micro flash /tmp/micro_speech zephyr -o zephyr_board=stm32f746g_disco $ tvmc run --device micro /tmp/micro_speech --options zephyr_board=stm32f746g_disco --print-top 6 --fill-mode random MLF found, using micro target runner. [[ 3 2 1 0] [ 35 -63 -100 -128]] ``` A Pre-RFC will be published soon associated to this patchset to start a discussion about that new context in TVMC. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
