Closed vvolhejn closed 2 years ago
Running into some trouble for inverted bottleneck models as well: https://discuss.tvm.apache.org/t/autotvm-fails-with-could-not-find-any-valid-schedule-for-task-task-func-name-conv2d-nchwc-x86/13024
Decided not to do this due to the issues mentioned above.
There is some issue when tuning the dilated conv models:
Seems related to this issue: https://discuss.tvm.apache.org/t/autoscheduler-failed-to-find-a-valid-schedule/11001
Tuning with dynamic quantization leads to
LLVM ERROR: Do not know how to split the result of this operator!