Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Remove unnecessary wait in case of failed stub creation #7192

Open
wants to merge 7 commits into
base: main
Choose a base branch
from
Open

Remove unnecessary wait in case of failed stub creation #7192

Show file tree
Hide file tree
Changes from 5 commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
7f02ab0
Remove unnecessary wait in case of failed stub creation
indrajit96 May 7, 2024
b5312ef
Pre-Commit fix
indrajit96 May 7, 2024
1cad688
Fix pipeline
indrajit96 May 8, 2024
48d431e
Pre-commit
indrajit96 May 8, 2024
4aee046
Review Comments fixed
indrajit96 May 8, 2024
de7fe55
Pipeline crash fix
indrajit96 May 8, 2024
12469d8
Merge branch 'main' into indrajit_DLIS-5819
indrajit96 May 9, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
17 changes: 17 additions & 0 deletions qa/L0_backend_python/model_control/model_control_test.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -82,6 +82,23 @@ def test_model_reload(self):
self.assertFalse(client.is_model_ready(model_name))
self.assertFalse(client.is_model_ready(ensemble_model_name))

def test_faulty_model_load(self):
working_model_name = "identity_fp32"
faulty_model_name = "auto_complete_error"
with httpclient.InferenceServerClient(f"{_tritonserver_ipaddr}:8000") as client:
# Load a correct model
client.load_model(working_model_name)
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Can you add a comment why a working model is required to reproduce the issue?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I am still trying to figure this out.
I think we can merge this Test for 24.05 and meanwhile I will continue my investigation.
We have already merged the python backend change.

# Load a faulty model
with self.assertRaises(InferenceServerException) as cm:
_ = client.load_model(faulty_model_name)
self.assertIn("load failed for model", str(cm.exception))

# Check if server is responsive
self.assertTrue(client.is_model_ready(working_model_name))
# Verify faulty model is not loaded
self.assertFalse(client.is_model_ready(faulty_model_name))
client.unload_model(working_model_name)


if __name__ == "__main__":
unittest.main()
3 changes: 3 additions & 0 deletions qa/L0_backend_python/model_control/test.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -37,6 +37,9 @@ source ../../common/util.sh

mkdir -p models/identity_fp32/1/
mkdir -p models/simple_identity_fp32/1/
mkdir -p models/auto_complete_error/1/

cp ../../python_models/auto_complete_error/model.py ./models/auto_complete_error/1/
cp ../../python_models/identity_fp32/model.py ./models/identity_fp32/1/model.py
cp ../../python_models/identity_fp32/config.pbtxt ./models/identity_fp32/config.pbtxt
cp ../../python_models/simple_identity_fp32/config.pbtxt ./models/simple_identity_fp32/config.pbtxt
Expand Down
Loading