junrushao commented on code in PR #12948:
URL: https://github.com/apache/tvm/pull/12948#discussion_r1018262909
##########
python/tvm/meta_schedule/testing/tune_utils.py:
##########
@@ -192,3 +192,50 @@ def f_time_per_layer(
)
return f_time_per_layer
+
+
+def create_computer(backend: str) -> Callable:
+ """Create a function to fetch the computing result of running the given
runtime module.
+
+ Parameters
+ ----------
+ backend : str
+ The backend to use, graph / vm.
Review Comment:
```suggestion
The backend to use, graph / vm / tir. Only tir is supported for now.
```
--
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]
