tqchen commented on a change in pull request #5690:
URL: https://github.com/apache/incubator-tvm/pull/5690#discussion_r432187036
##########
File path: tests/python/relay/test_pass_annotation.py
##########
@@ -538,9 +539,10 @@ def expected():
expected_index = [2, 2, 2, 1, 1, 1, 2, 2]
check_annotated_graph(annotated_func, expected_func)
params = {"a": a_data, "b": b_data, "c": c_data, "d": d_data}
- config = {"opt_level": 0}
- config["fallback_device"] = fallback_device
- with relay.build_config(**config):
+ fall_dev = tvm.tir.IntImm("int32", fallback_device.device_type)
+ with tvm.transform.PassContext(opt_level=0,
+ config={"relay.fallback_device_type":
+ tvm.tir.IntImm(32, fall_dev)}):
Review comment:
do we ned the intimm? I feel that conversion from int to the intImm is
automatic
----------------------------------------------------------------
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.
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
