[Apache TVM Discuss] [Questions] AutoTVM vs AutoScheduler tuning metrics

2021-06-23 Thread Caleb via Apache TVM Discuss
Thanks for this detailed reply, this was very helpful. Just to clarify, when you refer to a "schedule candidate" or the "best schedule", you're referring to the configuration of a specific operator (or task) on the hardware target, correct? --- [Visit Topic](https://discuss.tvm.apache.or

[Apache TVM Discuss] [Questions] AutoTVM vs AutoScheduler tuning metrics

2021-06-22 Thread Caleb via Apache TVM Discuss
Hello, I'm new to TVM and am exploring the tvmc application. I've tuned a couple models using TVMC and have the following questions about the tuning metrics: 1. When tuning using AutoTVM (`tvmc tune` with `--enable-autoscheduler` disabled), one of the metrics printed in the console is Curren

[Apache TVM Discuss] [Questions] Saving compiled model to a .tar file using Python API

2021-06-21 Thread Caleb via Apache TVM Discuss
Ultimately, I'm trying to save off a tuned model as an executable (or something similar). I'm wondering if this should be done between the `tune` and `compile` steps, or between the `compile` and `run` steps. However, I'm a little confused on the difference between the `TVMCModel` and `TVMCPac