Skip to content

fix: fix ml_inf to ml_inf1 in Neo multi-version support #3405

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.

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

Merged
merged 1 commit into from
Dec 2, 2022
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
2 changes: 1 addition & 1 deletion src/sagemaker/model.py
Original file line number Diff line number Diff line change
Expand Up @@ -789,7 +789,7 @@ def multi_version_compilation_supported(
}
if target_instance_type in NEO_IOC_TARGET_DEVICES:
return framework in multi_version_frameworks_support_mapping["neo_ioc_targets"]
if target_instance_type == "ml_inf":
if target_instance_type == "ml_inf1":
return framework in multi_version_frameworks_support_mapping["inferentia"]
return False

Expand Down
6 changes: 3 additions & 3 deletions tests/unit/sagemaker/model/test_neo.py
Original file line number Diff line number Diff line change
Expand Up @@ -47,7 +47,7 @@ def test_compile_model_for_inferentia(sagemaker_session):
)
model = _create_model(sagemaker_session)
model.compile(
target_instance_family="ml_inf",
target_instance_family="ml_inf1",
input_shape={"data": [1, 3, 1024, 1024]},
output_path="s3://output",
role="role",
Expand Down Expand Up @@ -313,7 +313,7 @@ def test_compile_with_pytorch_neo_in_ml_inf(session):

model = _create_model()
model.compile(
target_instance_family="ml_inf",
target_instance_family="ml_inf1",
input_shape={"data": [1, 3, 1024, 1024]},
output_path="s3://output",
role="role",
Expand All @@ -336,7 +336,7 @@ def test_compile_with_tensorflow_neo_in_ml_inf(session):

model = _create_model()
model.compile(
target_instance_family="ml_inf",
target_instance_family="ml_inf1",
input_shape={"data": [1, 3, 1024, 1024]},
output_path="s3://output",
role="role",
Expand Down