comaniac edited a comment on issue #6634: URL: https://github.com/apache/incubator-tvm/issues/6634#issuecomment-704475952
I see, so the same setting and tuning task work with the Python APIs but not the C++ APIs. Then it might be something that has been handled in the Python API before passing to the C++. Could you try to create an RPC runner by referring to https://github.com/apache/incubator-tvm/blob/master/python/tvm/auto_scheduler/measure.py#L399-L414 to see if that works or not? This also includes the `arch` issue you have already resolved. ---------------------------------------------------------------- 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. For queries about this service, please contact Infrastructure at: [email protected]
