guberti opened a new pull request, #11782: URL: https://github.com/apache/tvm/pull/11782
This PR adds utilities for autotuning with microTVM and evaluating the subsequently generated AOT-compiled model to `tvm.micro.testing`. A example end-to-end autotuning test is also added to `tests/micro/common/test_autotune.py`, which works for Arduino and Zephyr. This will be the only working autotuning test for microTVM, but it will not be run on the CI, as `@tvm.testing.requires_micro` is set (it requires physical hardware). The test takes about three minutes to run on the Sony Spresense. A few other changes in this PR: - A `fetch_model_from_url` function is added to reduce redundant logic for importing models - The tests in `tests/micro/common` are changed to be parameterized with the platform as well as the board. This eliminates the need for tests to decide whether a board is an Arduino or Zephyr board, and allows us to support boards that are compatible with both. - Explicitly declares the `requires_hardware` marker to remove a `pytest` warning. -- 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]
