tvalentyn commented on code in PR #27603:
URL: https://github.com/apache/beam/pull/27603#discussion_r1279934186


##########
sdks/python/apache_beam/ml/inference/base_test.py:
##########
@@ -964,6 +982,117 @@ def test_child_class_without_env_vars(self):
       actual = pcoll | base.RunInference(FakeModelHandlerNoEnvVars())
       assert_that(actual, equal_to(expected), label='assert:inferences')
 
+  def test_model_manager_loads_shared_model(self):

Review Comment:
   How about we add a test that  existing model references are still valid 
after we loaded more models than max_model ?



##########
sdks/python/apache_beam/ml/inference/base_test.py:
##########
@@ -964,6 +982,117 @@ def test_child_class_without_env_vars(self):
       actual = pcoll | base.RunInference(FakeModelHandlerNoEnvVars())
       assert_that(actual, equal_to(expected), label='assert:inferences')
 
+  def test_model_manager_loads_shared_model(self):

Review Comment:
   How about we add a test that  existing model references are still valid 
after we loaded more models than max_model ?



-- 
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