We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
inf2
HuggingFaceModel
1 parent 8794f8a commit 22cfd1aCopy full SHA for 22cfd1a
src/sagemaker/huggingface/model.py
@@ -303,9 +303,11 @@ def deploy(
303
"""
304
305
if not self.image_uri and instance_type is not None and instance_type.startswith("ml.inf"):
306
+ inference_tool = "neuron" if instance_type.startswith("ml.inf1") else "neuronx"
307
self.image_uri = self.serving_image_uri(
308
region_name=self.sagemaker_session.boto_session.region_name,
309
instance_type=instance_type,
310
+ inference_tool=inference_tool,
311
)
312
313
return super(HuggingFaceModel, self).deploy(
0 commit comments