masahi commented on code in PR #10876:
URL: https://github.com/apache/tvm/pull/10876#discussion_r843202250
##########
python/tvm/meta_schedule/testing/utils.py:
##########
@@ -110,3 +116,46 @@ def initialize_with_tune_context(self, context:
"TuneContext") -> None:
def apply(self, trace: Trace, _) -> Optional[Trace]:
return Trace(trace.insts, {})
+
+
+def apply_fixed_schedules(
+ relay_mod: Union[RelayFunc, IRModule],
+ target: Union[str, Target],
+ params: Optional[Dict[str, NDArray]],
+ schedule_fn: Callable[[ExtractedTask, Schedule], bool],
+):
+ """Apply fixed schedules (manually written, without any tunable knobs) as
specified by
+ schedule_fn to extracted tasks, and return a database that can be passed
to ApplyHistoryBest.
+
+ Parameters
+ ----------
+ mod : Union[RelayFunc, IRModule]
+ The Relay module to apply fixed schedules.
+ target : Union[str, Target]
+ The target used to extract tasks.
+ params : Optional[Dict[str, tvm.runtime.NDArray]]
+ The associated parameters of the module.
+ schedule_fn : Callable[[ExtractedTask, Schedule], bool]
Review Comment:
There are some cases where having the relay mod is required. For example, I
want to be able to skip tasks based on the output dtype of the compute, which
can be retrieved from the relay mod.
--
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]
