Skip to content

fix: factor in set instance type when building JumpStart models in ModelBuilder. #5093

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 7 commits into from
Mar 20, 2025
Merged
1 change: 1 addition & 0 deletions src/sagemaker/serve/builder/jumpstart_builder.py
Original file line number Diff line number Diff line change
Expand Up @@ -157,6 +157,7 @@ def _create_pre_trained_js_model(self) -> Type[Model]:
vpc_config=self.vpc_config,
sagemaker_session=self.sagemaker_session,
name=self.name,
instance_type=self.instance_type,
)

self._original_deploy = pysdk_model.deploy
Expand Down
4 changes: 3 additions & 1 deletion tests/integ/sagemaker/serve/test_schema_builder.py
Original file line number Diff line number Diff line change
Expand Up @@ -34,7 +34,9 @@

def test_model_builder_happy_path_with_only_model_id_text_generation(sagemaker_session):
model_builder = ModelBuilder(
model="HuggingFaceH4/zephyr-7b-beta", sagemaker_session=sagemaker_session
model="HuggingFaceH4/zephyr-7b-beta",
sagemaker_session=sagemaker_session,
instance_type=None,
)

model = model_builder.build(sagemaker_session=sagemaker_session)
Expand Down