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

Fix ORT execution provider test for onnxruntime v1.16.0 #1406

Merged
merged 1 commit into from
Sep 21, 2023
Merged

Fix ORT execution provider test for onnxruntime v1.16.0 #1406

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
13 changes: 5 additions & 8 deletions tests/onnxruntime/test_modeling.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -357,25 +357,22 @@ def test_missing_execution_provider(self):

if not is_onnxruntime_gpu_installed:
for provider in ["CUDAExecutionProvider", "TensorrtExecutionProvider"]:
with self.assertRaises(ImportError) as cm:
with self.assertRaises(ValueError) as cm:
_ = ORTModel.from_pretrained(self.ONNX_MODEL_ID, provider=provider)

self.assertTrue(
f"Asked to use {provider}, but `onnxruntime-gpu` package was not found." in str(cm.exception)
)
self.assertTrue("but the available execution providers" in str(cm.exception))

else:
logger.info("Skipping CUDAExecutionProvider/TensorrtExecutionProvider without `onnxruntime-gpu` test")

# need to install first onnxruntime-gpu, then onnxruntime for this test to pass,
# thus overwritting onnxruntime/capi/_ld_preload.py
if is_onnxruntime_installed and is_onnxruntime_gpu_installed:
for provider in ["CUDAExecutionProvider", "TensorrtExecutionProvider"]:
with self.assertRaises(ImportError) as cm:
with self.assertRaises(ValueError) as cm:
_ = ORTModel.from_pretrained(self.ONNX_MODEL_ID, provider=provider)

self.assertTrue(
"`onnxruntime-gpu` is installed, but GPU dependencies are not loaded." in str(cm.exception)
)
self.assertTrue("but the available execution providers" in str(cm.exception))
else:
logger.info("Skipping double onnxruntime + onnxruntime-gpu install test")

Expand Down