shingjan commented on a change in pull request #8492:
URL: https://github.com/apache/tvm/pull/8492#discussion_r685604078



##########
File path: python/tvm/auto_scheduler/measure.py
##########
@@ -817,21 +818,63 @@ def prepare_input_map(args):
     return tensor_input_map
 
 
+def prepare_runner_args(inp, build_res):
+    """This function prepare the arguments for local/rpc runner in main process

Review comment:
       done

##########
File path: python/tvm/auto_scheduler/measure.py
##########
@@ -817,21 +818,63 @@ def prepare_input_map(args):
     return tensor_input_map
 
 
+def prepare_runner_args(inp, build_res):
+    """This function prepare the arguments for local/rpc runner in main process
+    Parameters
+    ----------
+    inp : MeasureInput
+        Measure input to be measured.
+
+    build_res : BuildResult
+        Build result to be measured.
+
+    Returns
+    -------
+    List[Optional[numpy.ndarray]] :
+        List of numpy.ndarray representation of task input buffer. None if 
argument not present in task_input_names.

Review comment:
       done

##########
File path: python/tvm/auto_scheduler/measure.py
##########
@@ -817,21 +819,63 @@ def prepare_input_map(args):
     return tensor_input_map
 
 
+def prepare_runner_args(inp, build_res):
+    """This function prepare the arguments for local/rpc runner in main process
+    Parameters
+    ----------
+    inp : MeasureInput
+        Measure input to be measured.
+
+    build_res : BuildResult
+        Build result to be measured.
+
+    Returns
+    -------
+    List[NDArray, None] :

Review comment:
       done

##########
File path: python/tvm/auto_scheduler/measure.py
##########
@@ -62,6 +63,7 @@
     deserialize_workload_registry_entry,
 )
 
+

Review comment:
       done




-- 
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]


Reply via email to