Merge branch 'master' into feat/jumpstart-extract-generated-text-from-response

Author: evakravi

CHANGELOG.md

@@ -1,5 +1,28 @@
 # Changelog
 
+## v2.193.0 (2023-10-18)
+
+### Features
+
+ * jumpstart model artifact instance type variants
+ * jumpstart instance specific hyperparameters
+ * Feature Processor event based triggers (#1132)
+ * Support job checkpoint in remote function
+ * jumpstart model package arn instance type variants
+
+### Bug Fixes and Other Changes
+
+ * Fix hyperlinks in feature_processor.scheduler parameter descriptions
+ * add image_uris_unit_test pytest mark
+ * bump apache-airflow to `v2.7.2`
+ * clone distribution in validate_distribution
+ * fix flaky Inference Recommender integration tests
+
+### Documentation Changes
+
+ * Update PipelineModel.register documentation
+ * specify that input_shape in no longer required for torch 2.0 mod…
+
 ## v2.192.1 (2023-10-13)
 
 ### Bug Fixes and Other Changes

VERSION

@@ -1 +1 @@
-2.192.2.dev0
+2.193.1.dev0

doc/amazon_sagemaker_featurestore.rst

@@ -230,9 +230,11 @@ The following code from the fraud detection example shows a minimal
        enable_online_store=True
    )
 
-Creating a feature group takes time as the data is loaded. You will need
-to wait until it is created before you can use it. You can check status
-using the following method.
+Creating a feature group takes time as the data is loaded. You will
+need to wait until it is created before you can use it. You can
+check status using the following method. Note that it can take
+approximately 10-15 minutes to provision an online ``FeatureGroup``
+with the ``InMemory`` ``StorageType``.
 
 .. code:: python
 
@@ -480,7 +482,9 @@ Feature Store `DatasetBuilder API Reference
 .. rubric:: Delete a feature group
    :name: bCe9CA61b78
 
-You can delete a feature group with the ``delete`` function.
+You can delete a feature group with the ``delete`` function. Note that it
+can take approximately 10-15 minutes to delete an online ``FeatureGroup``
+with the ``InMemory`` ``StorageType``.
 
 .. code:: python
 

requirements/extras/test_requirements.txt

@@ -12,7 +12,7 @@ awslogs==0.14.0
 black==22.3.0
 stopit==1.1.2
 # Update tox.ini to have correct version of airflow constraints file
-apache-airflow==2.7.1
+apache-airflow==2.7.2
 apache-airflow-providers-amazon==7.2.1
 attrs>=23.1.0,<24
 fabric==2.6.0

src/sagemaker/djl_inference/model.py

@@ -781,7 +781,7 @@ def serving_image_uri(self, region_name):
             str: The appropriate image URI based on the given parameters.
         """
         if not self.djl_version:
-            self.djl_version = "0.23.0"
+            self.djl_version = "0.24.0"
 
         return image_uris.retrieve(
             self._framework(),

src/sagemaker/feature_store/feature_processor/feature_scheduler.py

@@ -281,13 +281,13 @@ def schedule(
     Args:
         pipeline_name (str): The SageMaker Pipeline name that will be scheduled.
         schedule_expression (str): The expression that defines when the schedule runs. It supports
-            at expression, rate expression and cron expression. See https://docs.aws.amazon.com/
-            scheduler/latest/APIReference/API_CreateSchedule.html#scheduler-CreateSchedule-request
-            -ScheduleExpression for more details.
+            at expression, rate expression and cron expression. See '''https://docs.aws.amazon.com\
+                /scheduler/latest/APIReference/API_CreateSchedule.html#scheduler-CreateSchedule-\
+                request-ScheduleExpression''' for more details.
         state (str): Specifies whether the schedule is enabled or disabled. Valid values are
-            ENABLED and DISABLED. See https://docs.aws.amazon.com/scheduler/latest/APIReference/
-            API_CreateSchedule.html#scheduler-CreateSchedule-request-State for more details.
-            If not specified, it will default to ENABLED.
+            ENABLED and DISABLED. See '''https://docs.aws.amazon.com/scheduler/latest/APIReference\
+                /API_CreateSchedule.html#scheduler-CreateSchedule-request-State'''
+            for more details. If not specified, it will default to ENABLED.
         start_date (Optional[datetime]): The date, in UTC, after which the schedule can begin
             invoking its target. Depending on the schedule’s recurrence expression, invocations
             might occur on, or after, the StartDate you specify.

src/sagemaker/huggingface/llm_utils.py

@@ -51,6 +51,6 @@ def get_huggingface_llm_image_uri(
             image_scope="inference",
         )
     if backend == "lmi":
-        version = version or "0.23.0"
+        version = version or "0.24.0"
         return image_uris.retrieve(framework="djl-deepspeed", region=region, version=version)
     raise ValueError("Unsupported backend: %s" % backend)

src/sagemaker/image_uri_config/djl-deepspeed.json

@@ -1,6 +1,37 @@
 {
     "scope": ["inference"],
     "versions": {
+         "0.24.0": {
+            "registries": {
+                "af-south-1": "626614931356",
+                "il-central-1": "780543022126",
+                "ap-east-1": "871362719292",
+                "ap-northeast-1": "763104351884",
+                "ap-northeast-2": "763104351884",
+                "ap-northeast-3": "364406365360",
+                "ap-south-1": "763104351884",
+                "ap-southeast-1": "763104351884",
+                "ap-southeast-2": "763104351884",
+                "ap-southeast-3": "907027046896",
+                "ca-central-1": "763104351884",
+                "cn-north-1": "727897471807",
+                "cn-northwest-1": "727897471807",
+                "eu-central-1": "763104351884",
+                "eu-north-1": "763104351884",
+                "eu-west-1": "763104351884",
+                "eu-west-2": "763104351884",
+                "eu-west-3": "763104351884",
+                "eu-south-1": "692866216735",
+                "me-south-1": "217643126080",
+                "sa-east-1": "763104351884",
+                "us-east-1": "763104351884",
+                "us-east-2": "763104351884",
+                "us-west-1": "763104351884",
+                "us-west-2": "763104351884"
+            },
+            "repository": "djl-inference",
+            "tag_prefix": "0.24.0-deepspeed0.10.0-cu118"
+        },
          "0.23.0": {
             "registries": {
                 "af-south-1": "626614931356",

src/sagemaker/image_uri_config/djl-fastertransformer.json

@@ -1,6 +1,37 @@
 {
     "scope": ["inference"],
     "versions": {
+        "0.24.0": {
+            "registries": {
+                "af-south-1": "626614931356",
+                "il-central-1": "780543022126",
+                "ap-east-1": "871362719292",
+                "ap-northeast-1": "763104351884",
+                "ap-northeast-2": "763104351884",
+                "ap-northeast-3": "364406365360",
+                "ap-south-1": "763104351884",
+                "ap-southeast-1": "763104351884",
+                "ap-southeast-2": "763104351884",
+                "ap-southeast-3": "907027046896",
+                "ca-central-1": "763104351884",
+                "cn-north-1": "727897471807",
+                "cn-northwest-1": "727897471807",
+                "eu-central-1": "763104351884",
+                "eu-north-1": "763104351884",
+                "eu-west-1": "763104351884",
+                "eu-west-2": "763104351884",
+                "eu-west-3": "763104351884",
+                "eu-south-1": "692866216735",
+                "me-south-1": "217643126080",
+                "sa-east-1": "763104351884",
+                "us-east-1": "763104351884",
+                "us-east-2": "763104351884",
+                "us-west-1": "763104351884",
+                "us-west-2": "763104351884"
+            },
+            "repository": "djl-inference",
+            "tag_prefix": "0.24.0-fastertransformer5.3.0-cu118"
+        },
         "0.23.0": {
             "registries": {
                 "af-south-1": "626614931356",

src/sagemaker/jumpstart/artifacts/metric_definitions.py

@@ -34,6 +34,7 @@ def _retrieve_default_training_metric_definitions(
     tolerate_vulnerable_model: bool = False,
     tolerate_deprecated_model: bool = False,
     sagemaker_session: Session = DEFAULT_JUMPSTART_SAGEMAKER_SESSION,
+    instance_type: Optional[str] = None,
 ) -> Optional[List[Dict[str, str]]]:
     """Retrieves the default training metric definitions for the model.
 
@@ -55,6 +56,8 @@ def _retrieve_default_training_metric_definitions(
             object, used for SageMaker interactions. If not
             specified, one is created using the default AWS configuration
             chain. (Default: sagemaker.jumpstart.constants.DEFAULT_JUMPSTART_SAGEMAKER_SESSION).
+        instance_type (str): An instance type to optionally supply in order to get
+            metric definitions specific for the instance type.
     Returns:
         list: the default training metric definitions to use for the model or None.
     """
@@ -72,4 +75,29 @@ def _retrieve_default_training_metric_definitions(
         sagemaker_session=sagemaker_session,
     )
 
-    return deepcopy(model_specs.metrics) if model_specs.metrics else None
+    default_metric_definitions = (
+        deepcopy(model_specs.metrics) if getattr(model_specs, "metrics") else []
+    )
+
+    instance_specific_metric_definitions = (
+        model_specs.training_instance_type_variants.get_instance_specific_metric_definitions(
+            instance_type
+        )
+        if instance_type
+        and getattr(model_specs, "training_instance_type_variants", None) is not None
+        else []
+    )
+
+    instance_specific_metric_name: str
+    for instance_specific_metric_definition in instance_specific_metric_definitions:
+        instance_specific_metric_name = instance_specific_metric_definition["Name"]
+        default_metric_definitions = list(
+            filter(
+                lambda metric_definition: metric_definition["Name"]
+                != instance_specific_metric_name,
+                default_metric_definitions,
+            )
+        )
+        default_metric_definitions.append(instance_specific_metric_definition)
+
+    return default_metric_definitions

src/sagemaker/jumpstart/artifacts/model_uris.py

@@ -28,12 +28,68 @@
     verify_model_region_and_return_specs,
 )
 from sagemaker.session import Session
+from sagemaker.jumpstart.types import JumpStartModelSpecs
+
+
+def _retrieve_hosting_prepacked_artifact_key(
+    model_specs: JumpStartModelSpecs, instance_type: str
+) -> str:
+    """Returns instance specific hosting prepacked artifact key or default one as fallback."""
+    instance_specific_prepacked_hosting_artifact_key: Optional[str] = (
+        model_specs.hosting_instance_type_variants.get_instance_specific_prepacked_artifact_key(
+            instance_type=instance_type
+        )
+        if instance_type
+        and getattr(model_specs, "hosting_instance_type_variants", None) is not None
+        else None
+    )
+
+    default_prepacked_hosting_artifact_key: Optional[str] = getattr(
+        model_specs, "hosting_prepacked_artifact_key"
+    )
+
+    return (
+        instance_specific_prepacked_hosting_artifact_key or default_prepacked_hosting_artifact_key
+    )
+
+
+def _retrieve_hosting_artifact_key(model_specs: JumpStartModelSpecs, instance_type: str) -> str:
+    """Returns instance specific hosting artifact key or default one as fallback."""
+    instance_specific_hosting_artifact_key: Optional[str] = (
+        model_specs.hosting_instance_type_variants.get_instance_specific_artifact_key(
+            instance_type=instance_type
+        )
+        if instance_type
+        and getattr(model_specs, "hosting_instance_type_variants", None) is not None
+        else None
+    )
+
+    default_hosting_artifact_key: str = model_specs.hosting_artifact_key
+
+    return instance_specific_hosting_artifact_key or default_hosting_artifact_key
+
+
+def _retrieve_training_artifact_key(model_specs: JumpStartModelSpecs, instance_type: str) -> str:
+    """Returns instance specific training artifact key or default one as fallback."""
+    instance_specific_training_artifact_key: Optional[str] = (
+        model_specs.training_instance_type_variants.get_instance_specific_artifact_key(
+            instance_type=instance_type
+        )
+        if instance_type
+        and getattr(model_specs, "training_instance_type_variants", None) is not None
+        else None
+    )
+
+    default_training_artifact_key: str = model_specs.training_artifact_key
+
+    return instance_specific_training_artifact_key or default_training_artifact_key
 
 
 def _retrieve_model_uri(
     model_id: str,
     model_version: str,
     model_scope: Optional[str] = None,
+    instance_type: Optional[str] = None,
     region: Optional[str] = None,
     tolerate_vulnerable_model: bool = False,
     tolerate_deprecated_model: bool = False,
@@ -50,6 +106,7 @@ def _retrieve_model_uri(
             artifact S3 URI.
         model_scope (str): The model type, i.e. what it is used for.
             Valid values: "training" and "inference".
+        instance_type (str): The ML compute instance type for the specified scope. (Default: None).
         region (str): Region for which to retrieve model S3 URI. (Default: None).
         tolerate_vulnerable_model (bool): True if vulnerable versions of model
             specifications should be tolerated (exception not raised). If False, raises an
@@ -84,14 +141,21 @@ def _retrieve_model_uri(
         sagemaker_session=sagemaker_session,
     )
 
+    model_artifact_key: str
+
     if model_scope == JumpStartScriptScope.INFERENCE:
+
+        is_prepacked = not model_specs.use_inference_script_uri()
+
         model_artifact_key = (
-            getattr(model_specs, "hosting_prepacked_artifact_key", None)
-            or model_specs.hosting_artifact_key
+            _retrieve_hosting_prepacked_artifact_key(model_specs, instance_type)
+            if is_prepacked
+            else _retrieve_hosting_artifact_key(model_specs, instance_type)
         )
 
     elif model_scope == JumpStartScriptScope.TRAINING:
-        model_artifact_key = model_specs.training_artifact_key
+
+        model_artifact_key = _retrieve_training_artifact_key(model_specs, instance_type)
 
     bucket = os.environ.get(
         ENV_VARIABLE_JUMPSTART_MODEL_ARTIFACT_BUCKET_OVERRIDE

src/sagemaker/jumpstart/factory/estimator.py

@@ -475,6 +475,7 @@ def _add_model_uri_to_kwargs(kwargs: JumpStartEstimatorInitKwargs) -> JumpStartE
             tolerate_deprecated_model=kwargs.tolerate_deprecated_model,
             tolerate_vulnerable_model=kwargs.tolerate_vulnerable_model,
             sagemaker_session=kwargs.sagemaker_session,
+            instance_type=kwargs.instance_type,
         )
 
         if (
@@ -632,6 +633,7 @@ def _add_metric_definitions_to_kwargs(
             tolerate_deprecated_model=kwargs.tolerate_deprecated_model,
             tolerate_vulnerable_model=kwargs.tolerate_vulnerable_model,
             sagemaker_session=kwargs.sagemaker_session,
+            instance_type=kwargs.instance_type,
         )
         or []
     )