ConvolutedDog opened a new pull request, #18159: URL: https://github.com/apache/tvm/pull/18159
This PR introduces the max_trials_per_task parameter to the static_shape_tuning_pipeline, giving users explicit control over the maximum number of trials allocated to each task during MetaSchedule tuning. Currently, the default value is 64, so when tuning on the GPU, when the max_trials_per_task value given by the user is less than the number of tasks x 64 but greater than 64, some TIR funcs are not tuned and not bound to threads. -- 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]
