fix(instance-preferences): clear error on recipe trainers; no serializer warnings on submit

sagemaker-core/src/sagemaker/core/modules/configs.py

@@ -166,6 +166,10 @@ class Compute(shapes.ResourceConfig):
     def _model_validator(self) -> "Compute":
         """Convert Unassigned values to None and validate instance_preferences."""
         converted = convert_unassigned_to_none(self)
+        # Nested preferences keep Unassigned() on unset fields, which model_dump
+        # flags per element; normalise them the same way as the top level.
+        for preference in converted.instance_preferences or ():
+            convert_unassigned_to_none(preference)
         validate_instance_preferences(converted)
         return converted
 

sagemaker-core/src/sagemaker/core/training/configs.py

@@ -194,6 +194,10 @@ class Compute(shapes.ResourceConfig):
     def _model_validator(self) -> "Compute":
         """Convert Unassigned values to None and validate instance_preferences."""
         converted = convert_unassigned_to_none(self)
+        # Nested preferences keep Unassigned() on unset fields, which model_dump
+        # flags per element; normalise them the same way as the top level.
+        for preference in converted.instance_preferences or ():
+            convert_unassigned_to_none(preference)
         validate_instance_preferences(converted)
         return converted
 

sagemaker-core/tests/unit/test_compute_configs.py

@@ -1,6 +1,10 @@
 """Unit tests for Compute and HyperPodCompute config classes."""
 
+import warnings
+
 import pytest
+from sagemaker.core.modules.configs import Compute as ModulesCompute
+from sagemaker.core.shapes import InstancePreference
 from sagemaker.core.training.configs import Compute, HyperPodCompute
 
 
@@ -337,3 +341,25 @@ def test_processing_cluster_config_single_type_still_works(self):
         )
         assert pcc.instance_type == "ml.m5.xlarge"
         assert pcc.instance_count == 1
+
+
+class TestInstancePreferencesSerialization:
+    """Unset fields on nested preferences must not surface as pydantic
+    serializer warnings on every submit, and the request payload must omit them."""
+
+    @pytest.mark.parametrize("compute_cls", [Compute, ModulesCompute])
+    def test_to_resource_config_emits_no_serializer_warning(self, compute_cls):
+        compute = compute_cls(
+            instance_preferences=[
+                InstancePreference(instance_type="ml.m5.large"),
+                InstancePreference(instance_type="ml.m5.xlarge"),
+            ],
+            instance_count=1,
+        )
+        with warnings.catch_warnings():
+            warnings.simplefilter("error")
+            resource_config = compute._to_resource_config()
+        prefs = resource_config.instance_preferences
+        assert [p.instance_type for p in prefs] == ["ml.m5.large", "ml.m5.xlarge"]
+        assert all(p.training_plan_arns is None and p.instance_count is None for p in prefs)
+        assert resource_config.instance_count == 1

sagemaker-train/src/sagemaker/train/base_trainer.py

@@ -901,6 +901,15 @@ def _train_serverful_smtj(self, training_dataset=None, validation_dataset=None,
         role = self.role
 
         compute = self.compute
+        # Recipes are rendered for one instance type (device class, image,
+        # launcher), so a service-chosen type cannot apply. Fail before the
+        # recipe fetch, and before the type-enum check reports a confusing
+        # "Instance type 'None' is not supported".
+        if getattr(compute, "instance_preferences", None):
+            raise ValueError(
+                "Training recipes do not support ``instance_preferences``. "
+                "Set a single ``instance_type`` in Compute when using a recipe-based trainer."
+            )
         customization_technique = self._customization_technique
 
         # Resolve the recipe S3 URI from hub metadata

sagemaker-train/tests/unit/train/test_base_trainer_compute.py

@@ -112,6 +112,7 @@ def test_compute_attributes_forwarded(self):
         trainer = _ConcreteTrainer()
         trainer.compute = MagicMock(
             instance_type="ml.p4d.24xlarge",
+            instance_preferences=None,
             instance_count=4,
             volume_size_in_gb=300,
             keep_alive_period_in_seconds=1200,
@@ -131,6 +132,7 @@ def test_training_plan_arn_forwarded(self):
         trainer = _ConcreteTrainer()
         trainer.compute = MagicMock(
             instance_type="ml.p5.48xlarge",
+            instance_preferences=None,
             instance_count=2,
             volume_size_in_gb=500,
             keep_alive_period_in_seconds=0,
@@ -147,6 +149,7 @@ def test_training_plan_arn_none_when_not_set(self):
         trainer = _ConcreteTrainer()
         trainer.compute = MagicMock(
             instance_type="ml.p4d.24xlarge",
+            instance_preferences=None,
             instance_count=1,
             volume_size_in_gb=30,
             keep_alive_period_in_seconds=0,

sagemaker-train/tests/unit/train/test_base_trainer_serverful.py

@@ -29,6 +29,7 @@ def __init__(self, **kwargs):
         self.compute = MagicMock(
             instance_type="ml.p4d.24xlarge",
             instance_count=1,
+            instance_preferences=None,
             volume_size_in_gb=100,
             keep_alive_period_in_seconds=None,
             training_plan_arn=None,
@@ -388,3 +389,36 @@ def test_skips_validation_when_enum_unavailable(self, mock_enum):
 
         # Any instance type is accepted; the method returns None to signal skip.
         assert trainer._validate_instance_type("ml.g5.xlarge", MagicMock()) is None
+
+
+class TestInstancePreferencesRejected:
+    """Recipes are rendered for one instance type, so a preference list must be
+    refused up front -- before the recipe fetch, and before the instance-type
+    enum check can report a misleading "Instance type 'None' is not supported"."""
+
+    @pytest.fixture
+    def trainer(self):
+        trainer = _ConcreteTrainer()
+        trainer.compute = MagicMock(
+            instance_type=None,
+            instance_count=2,
+            instance_preferences=[MagicMock(instance_type="ml.p5.48xlarge")],
+        )
+        return trainer
+
+    def test_rejected_before_any_recipe_or_network_access(self, trainer):
+        with patch("sagemaker.train.base_trainer.get_recipe_s3_uri") as fetch, pytest.raises(
+            ValueError, match="Training recipes do not support ``instance_preferences``"
+        ):
+            trainer._train_serverful_smtj(training_dataset="s3://bucket/train.jsonl")
+        fetch.assert_not_called()
+
+    def test_message_names_the_fix(self, trainer):
+        with pytest.raises(ValueError, match="Set a single ``instance_type`` in Compute"):
+            trainer._train_serverful_smtj(training_dataset="s3://bucket/train.jsonl")
+
+    def test_single_instance_type_is_unaffected(self):
+        trainer = _ConcreteTrainer()
+        _, kwargs = _run_serverful(trainer)
+        assert kwargs["compute"].instance_type == "ml.p4d.24xlarge"
+        assert not kwargs["compute"].instance_preferences

sagemaker-train/tests/unit/train/test_serverful_recipe_validation.py

@@ -38,6 +38,7 @@ def __init__(self, **kwargs):
         self.validation_dataset = None
         self.compute = MagicMock(
             instance_type="ml.p5.48xlarge",
+            instance_preferences=None,
             instance_count=4,
             volume_size_in_gb=100,
             keep_alive_period_in_seconds=None,