Merge branch 'master' into master

Author: rvasahu-amazon

CHANGELOG.md

@@ -1,5 +1,31 @@
 # Changelog
 
+## v2.213.0 (2024-03-15)
+
+### Features
+
+ * Add support for Streaming Inference
+ * tgi optimum 0.0.19, 0.0.20 releases
+ * support JumpStart proprietary models
+ * Add ModelDataSource and SourceUri support for model package and while registering
+ * Accept user-defined env variables for the entry-point
+ * Add overriding logic in ModelBuilder when task is provided
+
+### Bug Fixes and Other Changes
+
+ * Improvement of the tuner documentation
+ * Skip of tests which are long running and causing the ResourceLimitInUse exception
+ * Add AutoML -> AutoMLV2 mapper
+ * add ci-health checks
+ * split coverage out from testenv in tox.ini
+ * add PT 2.2 support for smdistributed, pytorchddp, and torch_distributed distributions
+ * sagemaker session region not being used
+ * chore: emit warning when no instance specific gated training env var is available, and raise exception when accept_eula flag is not supplied
+ * enable github actions for PRs
+ * Move sagemaker pysdk version check after bootstrap in remote job
+ * make unit tests compatible with pytest-xdist
+ * Update tblib constraint
+
 ## v2.212.0 (2024-03-06)
 
 ### Features

VERSION

@@ -1 +1 @@
-2.212.1.dev0
+2.213.1.dev0

src/sagemaker/tuner.py

@@ -11,6 +11,7 @@
 # ANY KIND, either express or implied. See the License for the specific
 # language governing permissions and limitations under the License.
 """Placeholder docstring"""
+
 from __future__ import absolute_import
 
 import importlib
@@ -641,8 +642,11 @@ def __init__(
                 extract the metric from the logs. This should be defined only
                 for hyperparameter tuning jobs that don't use an Amazon
                 algorithm.
-            strategy (str or PipelineVariable): Strategy to be used for hyperparameter estimations
-                (default: 'Bayesian').
+            strategy (str or PipelineVariable): Strategy to be used for hyperparameter estimations.
+                More information about different strategies:
+                https://docs.aws.amazon.com/sagemaker/latest/dg/automatic-model-tuning-how-it-works.html.
+                Available options are: 'Bayesian', 'Random', 'Hyperband',
+                'Grid' (default: 'Bayesian')
             objective_type (str or PipelineVariable): The type of the objective metric for
                 evaluating training jobs. This value can be either 'Minimize' or
                 'Maximize' (default: 'Maximize').
@@ -759,7 +763,8 @@ def __init__(
         self.autotune = autotune
 
     def override_resource_config(
-        self, instance_configs: Union[List[InstanceConfig], Dict[str, List[InstanceConfig]]]
+        self,
+        instance_configs: Union[List[InstanceConfig], Dict[str, List[InstanceConfig]]],
     ):
         """Override the instance configuration of the estimators used by the tuner.
 
@@ -966,7 +971,7 @@ def fit(
         include_cls_metadata: Union[bool, Dict[str, bool]] = False,
         estimator_kwargs: Optional[Dict[str, dict]] = None,
         wait: bool = True,
-        **kwargs
+        **kwargs,
     ):
         """Start a hyperparameter tuning job.
 
@@ -1055,7 +1060,7 @@ def _fit_with_estimator_dict(self, inputs, job_name, include_cls_metadata, estim
             allowed_keys=estimator_names,
         )
 
-        for (estimator_name, estimator) in self.estimator_dict.items():
+        for estimator_name, estimator in self.estimator_dict.items():
             ins = inputs.get(estimator_name, None) if inputs is not None else None
             args = estimator_kwargs.get(estimator_name, {}) if estimator_kwargs is not None else {}
             self._prepare_estimator_for_tuning(estimator, ins, job_name, **args)
@@ -1282,7 +1287,7 @@ def _attach_with_training_details_list(cls, sagemaker_session, estimator_cls, jo
             objective_metric_name_dict=objective_metric_name_dict,
             hyperparameter_ranges_dict=hyperparameter_ranges_dict,
             metric_definitions_dict=metric_definitions_dict,
-            **init_params
+            **init_params,
         )
 
     def deploy(
@@ -1297,7 +1302,7 @@ def deploy(
         model_name=None,
         kms_key=None,
         data_capture_config=None,
-        **kwargs
+        **kwargs,
     ):
         """Deploy the best trained or user specified model to an Amazon SageMaker endpoint.
 
@@ -1363,7 +1368,7 @@ def deploy(
             model_name=model_name,
             kms_key=kms_key,
             data_capture_config=data_capture_config,
-            **kwargs
+            **kwargs,
         )
 
     def stop_tuning_job(self):

tests/integ/test_auto_ml_v2.py

@@ -50,6 +50,10 @@ def test_time_series_forecasting_session_job_name():
     return unique_name_from_base("ts-forecast-job", max_length=32)
 
 
+@pytest.mark.skip(
+    reason="The test is disabled because it's causing the ResourceLimit exception. \
+Please run that manually before the proper fix."
+)
 @pytest.mark.skipif(
     tests.integ.test_region() in tests.integ.NO_AUTO_ML_REGIONS,
     reason="AutoML is not supported in the region yet.",
@@ -116,6 +120,10 @@ def test_auto_ml_v2_describe_auto_ml_job(
     assert desc["OutputDataConfig"] == expected_default_output_config
 
 
+@pytest.mark.skip(
+    reason="The test is disabled because it's causing the ResourceLimit exception. \
+Please run that manually before the proper fix."
+)
 @pytest.mark.skipif(
     tests.integ.test_region() in tests.integ.NO_AUTO_ML_REGIONS,
     reason="AutoML is not supported in the region yet.",
@@ -181,6 +189,10 @@ def test_auto_ml_v2_attach(problem_type, job_name_fixture_key, sagemaker_session
     assert desc["OutputDataConfig"] == expected_default_output_config
 
 
+@pytest.mark.skip(
+    reason="The test is disabled because it's causing the ResourceLimit exception. \
+Please run that manually before the proper fix."
+)
 @pytest.mark.skipif(
     tests.integ.test_region() in tests.integ.NO_AUTO_ML_REGIONS,
     reason="AutoML is not supported in the region yet.",
@@ -258,6 +270,10 @@ def test_list_candidates(
         pytest.skip("The job hasn't finished yet")
 
 
+@pytest.mark.skip(
+    reason="The test is disabled because it's causing the ResourceLimit exception. \
+Please run that manually before the proper fix."
+)
 @pytest.mark.skipif(
     tests.integ.test_region() in tests.integ.NO_AUTO_ML_REGIONS,
     reason="AutoML is not supported in the region yet.",
@@ -329,6 +345,10 @@ def test_best_candidate(
         pytest.skip("The job hasn't finished yet")
 
 
+@pytest.mark.skip(
+    reason="The test is disabled because it's causing the ResourceLimit exception. \
+Please run that manually before the proper fix."
+)
 @pytest.mark.skipif(
     tests.integ.test_region() in tests.integ.NO_AUTO_ML_REGIONS
     or tests.integ.test_region() in tests.integ.NO_CANVAS_REGIONS,
@@ -423,6 +443,10 @@ def test_deploy_best_candidate(
         pytest.skip("The job hasn't finished yet")
 
 
+@pytest.mark.skip(
+    reason="The test is disabled because it's causing the ResourceLimit exception. \
+Please run that manually before the proper fix."
+)
 @pytest.mark.skipif(
     tests.integ.test_region() in tests.integ.NO_AUTO_ML_REGIONS,
     reason="AutoML is not supported in the region yet.",