[GitHub] [incubator-tvm] zhiics commented on a change in pull request #6464: [Relay]Some backend improvements for PT OD models

[GitBox <gi...@apache.org>]

zhiics commented on a change in pull request #6464:
URL: https://github.com/apache/incubator-tvm/pull/6464#discussion_r488065249



##########
File path: tests/python/relay/test_any.py
##########
@@ -1084,5 +1142,41 @@ def test_any_adv_index():
     check_result([np_data, np_index, np_index], mod, ref_res)
 
 
+def verify_any_repeat(data_shape, np_dshape, repeats, axis):
+    mod = tvm.IRModule()
+    dtype = "float32"
+    data = relay.var("data", shape=data_shape, dtype=dtype)
+    y = relay.repeat(data, repeats, axis)
+    mod["main"] = relay.Function([data], y)
+    np_data = np.random.uniform(size=np_dshape).astype(dtype)
+    ref_res = np.repeat(np_data, repeats, axis)
+    check_result([np_data], mod, ref_res)
+
+
+def test_any_repeat():

Review comment:
       to let the CI pick up gpu test, we need to decorate the test_xx with `@tvm.testing.uses_gpu`




----------------------------------------------------------------
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:
users@infra.apache.org