Merge branch 'master' into feature/modelcard-property

selvask-aws · web-flow · commit 895f099eda8d · 2024-06-12T22:29:51.000+05:30
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -1,5 +1,34 @@
 # Changelog
 
+## v2.222.1 (2024-06-12)
+
+### Bug Fixes and Other Changes
+
+ * First changes
+ * estimator.deploy not respecting instance type
+
+## v2.222.0 (2024-06-07)
+
+### Features
+
+ * jumpstart telemetry
+
+### Bug Fixes and Other Changes
+
+ * update image_uri_configs  06-06-2024 07:17:31 PST
+ * bump requests from 2.31.0 to 2.32.2 in /requirements/extras
+ * chore: add HF LLM neuronx 0.0.23 image
+ * Updates for DJL 0.28.0 release
+ * chore(deps): bump mlflow from 2.11.1 to 2.12.1 in /tests/data/serve_resources/mlflow/tensorflow
+ * chore(deps): bump mlflow from 2.11.1 to 2.12.1 in /tests/data/serve_resources/mlflow/xgboost
+ * chore(deps): bump mlflow from 2.10.2 to 2.12.1 in /tests/data/serve_resources/mlflow/pytorch
+ * chore(deps): bump apache-airflow from 2.9.0 to 2.9.1 in /requirements/extras
+ * chore(deps): bump requests from 2.31.0 to 2.32.2 in /tests/data/serve_resources/mlflow/pytorch
+ * Fix ci unit-tests
+ * Making project name in workflow files dynamic
+ * update image_uri_configs  05-29-2024 07:17:35 PST
+ * Update: SM Endpoint Routing Strategy Support.
+
 ## v2.221.1 (2024-05-22)
 
 ### Bug Fixes and Other Changes
diff --git a/VERSION b/VERSION
@@ -1 +1 @@
-2.221.2.dev0
+2.222.2.dev0
diff --git a/src/sagemaker/image_uri_config/pytorch.json b/src/sagemaker/image_uri_config/pytorch.json
@@ -82,7 +82,8 @@
             "1.13": "1.13.1",
             "2.0": "2.0.1",
             "2.1": "2.1.0",
-            "2.2": "2.2.0"
+            "2.2": "2.2.0",
+            "2.3": "2.3.0"
         },
         "versions": {
             "0.4.0": {
@@ -1054,6 +1055,47 @@
                     "us-west-2": "763104351884"
                 },
                 "repository": "pytorch-inference"
+            },
+            "2.3.0": {
+                "py_versions": [
+                    "py311"
+                ],
+                "registries": {
+                    "af-south-1": "626614931356",
+                    "ap-east-1": "871362719292",
+                    "ap-northeast-1": "763104351884",
+                    "ap-northeast-2": "763104351884",
+                    "ap-northeast-3": "364406365360",
+                    "ap-south-1": "763104351884",
+                    "ap-south-2": "772153158452",
+                    "ap-southeast-1": "763104351884",
+                    "ap-southeast-2": "763104351884",
+                    "ap-southeast-3": "907027046896",
+                    "ap-southeast-4": "457447274322",
+                    "ca-central-1": "763104351884",
+                    "ca-west-1": "204538143572",
+                    "cn-north-1": "727897471807",
+                    "cn-northwest-1": "727897471807",
+                    "eu-central-1": "763104351884",
+                    "eu-central-2": "380420809688",
+                    "eu-north-1": "763104351884",
+                    "eu-south-1": "692866216735",
+                    "eu-south-2": "503227376785",
+                    "eu-west-1": "763104351884",
+                    "eu-west-2": "763104351884",
+                    "eu-west-3": "763104351884",
+                    "il-central-1": "780543022126",
+                    "me-central-1": "914824155844",
+                    "me-south-1": "217643126080",
+                    "sa-east-1": "763104351884",
+                    "us-east-1": "763104351884",
+                    "us-east-2": "763104351884",
+                    "us-gov-east-1": "446045086412",
+                    "us-gov-west-1": "442386744353",
+                    "us-west-1": "763104351884",
+                    "us-west-2": "763104351884"
+                },
+                "repository": "pytorch-inference"
             }
         }
     },
diff --git a/src/sagemaker/jumpstart/factory/estimator.py b/src/sagemaker/jumpstart/factory/estimator.py
@@ -322,7 +322,12 @@ def get_deploy_kwargs(
         model_id=model_id,
         model_from_estimator=True,
         model_version=model_version,
-        instance_type=model_deploy_kwargs.instance_type if training_instance_type is None else None,
+        instance_type=(
+            model_deploy_kwargs.instance_type
+            if training_instance_type is None
+            or instance_type is not None  # always use supplied inference instance type
+            else None
+        ),
         region=region,
         image_uri=image_uri,
         source_dir=source_dir,
diff --git a/src/sagemaker/serve/builder/djl_builder.py b/src/sagemaker/serve/builder/djl_builder.py
@@ -265,6 +265,7 @@ def _djl_model_builder_deploy_wrapper(self, *args, **kwargs) -> Type[PredictorBa
             # if has not been built for local container we must use cache
             # that hosting has write access to.
             self.pysdk_model.env["TRANSFORMERS_CACHE"] = "/tmp"
+            self.pysdk_model.env["HF_HOME"] = "/tmp"
             self.pysdk_model.env["HUGGINGFACE_HUB_CACHE"] = "/tmp"
 
         if "endpoint_logging" not in kwargs:
diff --git a/src/sagemaker/serve/builder/tei_builder.py b/src/sagemaker/serve/builder/tei_builder.py
@@ -175,6 +175,7 @@ def _tei_model_builder_deploy_wrapper(self, *args, **kwargs) -> Type[PredictorBa
             # if has not been built for local container we must use cache
             # that hosting has write access to.
             self.pysdk_model.env["TRANSFORMERS_CACHE"] = "/tmp"
+            self.pysdk_model.env["HF_HOME"] = "/tmp"
             self.pysdk_model.env["HUGGINGFACE_HUB_CACHE"] = "/tmp"
 
         if "endpoint_logging" not in kwargs:
diff --git a/src/sagemaker/serve/builder/tgi_builder.py b/src/sagemaker/serve/builder/tgi_builder.py
@@ -214,6 +214,7 @@ def _tgi_model_builder_deploy_wrapper(self, *args, **kwargs) -> Type[PredictorBa
             # if has not been built for local container we must use cache
             # that hosting has write access to.
             self.pysdk_model.env["TRANSFORMERS_CACHE"] = "/tmp"
+            self.pysdk_model.env["HF_HOME"] = "/tmp"
             self.pysdk_model.env["HUGGINGFACE_HUB_CACHE"] = "/tmp"
 
         if "endpoint_logging" not in kwargs:
diff --git a/src/sagemaker/serve/model_server/djl_serving/server.py b/src/sagemaker/serve/model_server/djl_serving/server.py
@@ -19,6 +19,7 @@
 _DEFAULT_ENV_VARS = {
     "SERVING_OPTS": "-Dai.djl.logging.level=debug",
     "TRANSFORMERS_CACHE": "/opt/ml/model/",
+    "HF_HOME": "/opt/ml/model/",
     "HUGGINGFACE_HUB_CACHE": "/opt/ml/model/",
 }
 
diff --git a/src/sagemaker/serve/model_server/tei/server.py b/src/sagemaker/serve/model_server/tei/server.py
@@ -18,6 +18,7 @@
 _SHM_SIZE = "2G"
 _DEFAULT_ENV_VARS = {
     "TRANSFORMERS_CACHE": "/opt/ml/model/",
+    "HF_HOME": "/opt/ml/model/",
     "HUGGINGFACE_HUB_CACHE": "/opt/ml/model/",
 }
 
diff --git a/src/sagemaker/serve/model_server/tgi/server.py b/src/sagemaker/serve/model_server/tgi/server.py
@@ -17,6 +17,7 @@
 _SHM_SIZE = "2G"
 _DEFAULT_ENV_VARS = {
     "TRANSFORMERS_CACHE": "/opt/ml/model/",
+    "HF_HOME": "/opt/ml/model/",
     "HUGGINGFACE_HUB_CACHE": "/opt/ml/model/",
 }
 
diff --git a/tests/unit/sagemaker/jumpstart/estimator/test_estimator.py b/tests/unit/sagemaker/jumpstart/estimator/test_estimator.py
@@ -1532,6 +1532,9 @@ def test_estimator_sets_different_inference_instance_depending_on_training_insta
         estimator.deploy(image_uri="blah")
         assert mock_estimator_deploy.call_args[1]["instance_type"] == "ml.p4de.24xlarge"
 
+        estimator.deploy(image_uri="blah", instance_type="ml.quantum.large")
+        assert mock_estimator_deploy.call_args[1]["instance_type"] == "ml.quantum.large"
+
     @mock.patch("sagemaker.utils.sagemaker_timestamp")
     @mock.patch("sagemaker.jumpstart.estimator.validate_model_id_and_get_type")
     @mock.patch(
diff --git a/tests/unit/sagemaker/serve/model_server/tei/test_server.py b/tests/unit/sagemaker/serve/model_server/tei/test_server.py
@@ -66,6 +66,7 @@ def test_start_invoke_destroy_local_tei_server(self, mock_requests):
             volumes={PosixPath("model_path/code"): {"bind": "/opt/ml/model/", "mode": "rw"}},
             environment={
                 "TRANSFORMERS_CACHE": "/opt/ml/model/",
+                "HF_HOME": "/opt/ml/model/",
                 "HUGGINGFACE_HUB_CACHE": "/opt/ml/model/",
                 "KEY": "VALUE",
                 "SAGEMAKER_SERVE_SECRET_KEY": "secret_key",

Original file line number	Diff line number	Diff line change
`@@ -19,6 +19,7 @@`
`19`	`19`	`_DEFAULT_ENV_VARS = {`
`20`	`20`	`"SERVING_OPTS": "-Dai.djl.logging.level=debug",`
`21`	`21`	`"TRANSFORMERS_CACHE": "/opt/ml/model/",`
	`22`	`+ "HF_HOME": "/opt/ml/model/",`
`22`	`23`	`"HUGGINGFACE_HUB_CACHE": "/opt/ml/model/",`
`23`	`24`	`}`
`24`	`25`
Original file line number	Diff line number	Diff line change
`@@ -18,6 +18,7 @@`
`18`	`18`	`_SHM_SIZE = "2G"`
`19`	`19`	`_DEFAULT_ENV_VARS = {`
`20`	`20`	`"TRANSFORMERS_CACHE": "/opt/ml/model/",`
	`21`	`+ "HF_HOME": "/opt/ml/model/",`
`21`	`22`	`"HUGGINGFACE_HUB_CACHE": "/opt/ml/model/",`
`22`	`23`	`}`
`23`	`24`
Original file line number	Diff line number	Diff line change
`@@ -17,6 +17,7 @@`
`17`	`17`	`_SHM_SIZE = "2G"`
`18`	`18`	`_DEFAULT_ENV_VARS = {`
`19`	`19`	`"TRANSFORMERS_CACHE": "/opt/ml/model/",`
	`20`	`+ "HF_HOME": "/opt/ml/model/",`
`20`	`21`	`"HUGGINGFACE_HUB_CACHE": "/opt/ml/model/",`
`21`	`22`	`}`
`22`	`23`