Merge branch 'master-jumpstart-curated-hub' into curated_hub_tagris_copy

Author: chrstfu

.github/workflows/codebuild-ci.yml

@@ -0,0 +1,48 @@
+name: PR Checks
+on:
+  pull_request_target:
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.head_ref }}
+  cancel-in-progress: true
+
+permissions:
+  id-token: write # This is required for requesting the JWT
+
+jobs:
+  codestyle-doc-tests:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Configure AWS Credentials
+        uses: aws-actions/configure-aws-credentials@v4
+        with:
+          role-to-assume: ${{ secrets.CI_AWS_ROLE_ARN }}
+          aws-region: us-west-2
+          role-duration-seconds: 10800
+      - name: Run Codestyle & Doc Tests
+        uses: aws-actions/aws-codebuild-run-build@v1
+        with:
+          project-name: sagemaker-python-sdk-ci-codestyle-doc-tests
+          source-version-override: "pr/${{ github.event.pull_request.number }}"
+  unit-tests:
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ["py38", "py39", "py310"]
+    steps:
+      - name: Configure AWS Credentials
+        uses: aws-actions/configure-aws-credentials@v4
+        with:
+          role-to-assume: ${{ secrets.CI_AWS_ROLE_ARN }}
+          aws-region: us-west-2
+          role-duration-seconds: 10800
+      - name: Run Unit Tests
+        uses: aws-actions/aws-codebuild-run-build@v1
+        with:
+          project-name: sagemaker-python-sdk-ci-unit-tests
+          source-version-override: "pr/${{ github.event.pull_request.number }}"
+          env-vars-for-codebuild: |
+            PY_VERSION
+        env:
+          PY_VERSION: ${{ matrix.python-version }}

CHANGELOG.md

@@ -1,5 +1,55 @@
 # Changelog
 
+## v2.212.0 (2024-03-06)
+
+### Features
+
+- Update SM Python SDK for PT 2.2.0 SM DLC
+
+### Bug Fixes and Other Changes
+
+- Create custom tarfile extractall util to fix backward compatibility issue
+- Upgrade smp to version 2.2
+- Enhance model builder selection logic to include model size
+
+## v2.211.0 (2024-03-05)
+
+### Features
+
+- pin dll version to support python3.11 to the sdk
+- instance specific jumpstart host requirements
+- Add TensorFlow 2.14 image configs
+- Add AutoMLV2 support
+- Support selective pipeline execution between function step and regular step
+- Add new Triton DLC URIs
+
+### Bug Fixes and Other Changes
+
+- Skip No Canvas regions for test_deploy_best_candidate
+- make sure gpus are found in local_gpu run
+- Bump Apache Airflow version to 2.8.2
+- properly close sagemaker config file after loading config
+- remove enable_network_isolation from the python doc
+
+### Documentation Changes
+
+- Add doc for new feature processor APIs and classes
+
+## v2.210.0 (2024-02-28)
+
+### Features
+
+- Prepend SageMaker Studio App Type to boto3 User Agent string
+- TGI optimum 0.0.18 (general+llm)
+- TGI 1.4.2
+
+### Bug Fixes and Other Changes
+
+- tolerate vulnerable old model for integ test and temporarily skip test_list_jumpstart_models_script_filter
+- add missing regions to pytorch config
+- Add validation for sagemaker version on remote job
+- fixed implementation of fail_on_violation for transform with monitoring
+
 ## v2.209.0 (2024-02-24)
 
 ### Features

VERSION

@@ -1 +1 @@
-2.209.1.dev0
+2.212.1.dev0

doc/api/prep_data/feature_store.rst

@@ -60,6 +60,7 @@ Feature Definition
     :members:
     :show-inheritance:
 
+
 Inputs
 ******
 
@@ -181,9 +182,13 @@ Feature Processor Data Source
     :members:
     :show-inheritance:
 
+.. autoclass:: sagemaker.feature_store.feature_processor.PySparkDataSource
+    :members:
+    :show-inheritance:
 
-Feature Processor Scheduler
-***************************
+
+Feature Processor Scheduler and Triggers
+****************************************
 
 .. automethod:: sagemaker.feature_store.feature_processor.to_pipeline
 
@@ -196,3 +201,12 @@ Feature Processor Scheduler
 .. automethod:: sagemaker.feature_store.feature_processor.describe
 
 .. automethod:: sagemaker.feature_store.feature_processor.list_pipelines
+
+.. automethod:: sagemaker.feature_store.feature_processor.put_trigger
+
+.. automethod:: sagemaker.feature_store.feature_processor.enable_trigger
+
+.. automethod:: sagemaker.feature_store.feature_processor.disable_trigger
+
+.. automethod:: sagemaker.feature_store.feature_processor.delete_trigger
+

doc/api/training/automlv2.rst

@@ -0,0 +1,7 @@
+AutoMLV2
+--------
+
+.. automodule:: sagemaker.automl.automlv2
+    :members:
+    :undoc-members:
+    :show-inheritance:

doc/api/training/index.rst

@@ -8,6 +8,7 @@ Training APIs
    algorithm
    analytics
    automl
+   automlv2
    debugger
    estimators
    tuner

doc/doc_utils/jumpstart_doc_utils.py

@@ -74,9 +74,12 @@ class Frameworks(str, Enum):
 
 JUMPSTART_REGION = "eu-west-2"
 SDK_MANIFEST_FILE = "models_manifest.json"
+PROPRIETARY_SDK_MANIFEST_FILE = "proprietary-sdk-manifest.json"
 JUMPSTART_BUCKET_BASE_URL = "https://jumpstart-cache-prod-{}.s3.{}.amazonaws.com".format(
     JUMPSTART_REGION, JUMPSTART_REGION
 )
+PROPRIETARY_DOC_BUCKET = "https://jumpstart-cache-prod-us-west-2.s3.us-west-2.amazonaws.com"
+
 TASK_MAP = {
     Tasks.IC: ProblemTypes.IMAGE_CLASSIFICATION,
     Tasks.IC_EMBEDDING: ProblemTypes.IMAGE_EMBEDDING,
@@ -152,18 +155,26 @@ class Frameworks(str, Enum):
 }
 
 
-def get_jumpstart_sdk_manifest():
-    url = "{}/{}".format(JUMPSTART_BUCKET_BASE_URL, SDK_MANIFEST_FILE)
+def get_public_s3_json_object(url):
     with request.urlopen(url) as f:
         models_manifest = f.read().decode("utf-8")
     return json.loads(models_manifest)
 
 
-def get_jumpstart_sdk_spec(key):
-    url = "{}/{}".format(JUMPSTART_BUCKET_BASE_URL, key)
-    with request.urlopen(url) as f:
-        model_spec = f.read().decode("utf-8")
-    return json.loads(model_spec)
+def get_jumpstart_sdk_manifest():
+    return get_public_s3_json_object(f"{JUMPSTART_BUCKET_BASE_URL}/{SDK_MANIFEST_FILE}")
+
+
+def get_proprietary_sdk_manifest():
+    return get_public_s3_json_object(f"{PROPRIETARY_DOC_BUCKET}/{PROPRIETARY_SDK_MANIFEST_FILE}")
+
+
+def get_jumpstart_sdk_spec(s3_key: str):
+    return get_public_s3_json_object(f"{JUMPSTART_BUCKET_BASE_URL}/{s3_key}")
+
+
+def get_proprietary_sdk_spec(s3_key: str):
+    return get_public_s3_json_object(f"{PROPRIETARY_DOC_BUCKET}/{s3_key}")
 
 
 def get_model_task(id):
@@ -196,6 +207,45 @@ def get_model_source(url):
         return "Source"
 
 
+def create_proprietary_model_table():
+    proprietary_content_intro = []
+    proprietary_content_intro.append("\n")
+    proprietary_content_intro.append(".. list-table:: Available Proprietary Models\n")
+    proprietary_content_intro.append("   :widths: 50 20 20 20 20\n")
+    proprietary_content_intro.append("   :header-rows: 1\n")
+    proprietary_content_intro.append("   :class: datatable\n")
+    proprietary_content_intro.append("\n")
+    proprietary_content_intro.append("   * - Model ID\n")
+    proprietary_content_intro.append("     - Fine Tunable?\n")
+    proprietary_content_intro.append("     - Supported Version\n")
+    proprietary_content_intro.append("     - Min SDK Version\n")
+    proprietary_content_intro.append("     - Source\n")
+
+    sdk_manifest = get_proprietary_sdk_manifest()
+    sdk_manifest_top_versions_for_models = {}
+
+    for model in sdk_manifest:
+        if model["model_id"] not in sdk_manifest_top_versions_for_models:
+            sdk_manifest_top_versions_for_models[model["model_id"]] = model
+        else:
+            if str(sdk_manifest_top_versions_for_models[model["model_id"]]["version"]) < str(
+                model["version"]
+            ):
+                sdk_manifest_top_versions_for_models[model["model_id"]] = model
+
+    proprietary_content_entries = []
+    for model in sdk_manifest_top_versions_for_models.values():
+        model_spec = get_proprietary_sdk_spec(model["spec_key"])
+        proprietary_content_entries.append("   * - {}\n".format(model_spec["model_id"]))
+        proprietary_content_entries.append("     - {}\n".format(False))  # TODO: support training
+        proprietary_content_entries.append("     - {}\n".format(model["version"]))
+        proprietary_content_entries.append("     - {}\n".format(model["min_version"]))
+        proprietary_content_entries.append(
+            "     - `{} <{}>`__ |external-link|\n".format("Source", model_spec.get("url"))
+        )
+    return proprietary_content_intro + proprietary_content_entries + ["\n"]
+
+
 def create_jumpstart_model_table():
     sdk_manifest = get_jumpstart_sdk_manifest()
     sdk_manifest_top_versions_for_models = {}
@@ -249,19 +299,19 @@ def create_jumpstart_model_table():
     file_content_intro.append("     - Source\n")
 
     dynamic_table_files = []
-    file_content_entries = []
+    open_weight_content_entries = []
 
     for model in sdk_manifest_top_versions_for_models.values():
         model_spec = get_jumpstart_sdk_spec(model["spec_key"])
         model_task = get_model_task(model_spec["model_id"])
         string_model_task = get_string_model_task(model_spec["model_id"])
         model_source = get_model_source(model_spec["url"])
-        file_content_entries.append("   * - {}\n".format(model_spec["model_id"]))
-        file_content_entries.append("     - {}\n".format(model_spec["training_supported"]))
-        file_content_entries.append("     - {}\n".format(model["version"]))
-        file_content_entries.append("     - {}\n".format(model["min_version"]))
-        file_content_entries.append("     - {}\n".format(model_task))
-        file_content_entries.append(
+        open_weight_content_entries.append("   * - {}\n".format(model_spec["model_id"]))
+        open_weight_content_entries.append("     - {}\n".format(model_spec["training_supported"]))
+        open_weight_content_entries.append("     - {}\n".format(model["version"]))
+        open_weight_content_entries.append("     - {}\n".format(model["min_version"]))
+        open_weight_content_entries.append("     - {}\n".format(model_task))
+        open_weight_content_entries.append(
             "     - `{} <{}>`__ |external-link|\n".format(model_source, model_spec["url"])
         )
 
@@ -299,7 +349,10 @@ def create_jumpstart_model_table():
             f.writelines(file_content_single_entry)
             f.close()
 
+    proprietary_content_entries = create_proprietary_model_table()
+
     f = open("doc_utils/pretrainedmodels.rst", "a")
     f.writelines(file_content_intro)
-    f.writelines(file_content_entries)
+    f.writelines(open_weight_content_entries)
+    f.writelines(proprietary_content_entries)
     f.close()

doc/requirements.txt

@@ -4,3 +4,4 @@ docutils==0.15.2
 packaging==20.9
 jinja2==3.1.3
 schema==0.7.5
+accelerate>=0.24.1,<=0.27.0

requirements/extras/huggingface_requirements.txt

@@ -0,0 +1 @@
+accelerate>=0.24.1,<=0.27.0

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==2.8.1
+apache-airflow==2.8.2
 apache-airflow-providers-amazon==7.2.1
 attrs>=23.1.0,<24
 fabric==2.6.0
@@ -39,3 +39,4 @@ tritonclient[http]<2.37.0
 onnx==1.14.1
 # tf2onnx==1.15.1
 nbformat>=5.9,<6
+accelerate>=0.24.1,<=0.27.0

setup.py

@@ -63,7 +63,7 @@ def read_requirements(filename):
     "PyYAML~=6.0",
     "jsonschema",
     "platformdirs",
-    "tblib>=1.7.0,<3",
+    "tblib>=1.7.0,<4",
     "urllib3>=1.26.8,<3.0.0",
     "requests",
     "docker",
@@ -79,6 +79,7 @@ def read_requirements(filename):
     "feature-processor": read_requirements(
         "requirements/extras/feature-processor_requirements.txt"
     ),
+    "huggingface": read_requirements("requirements/extras/huggingface_requirements.txt"),
 }
 # Meta dependency groups
 extras["all"] = [item for group in extras.values() for item in group]

src/sagemaker/__init__.py

@@ -61,6 +61,17 @@
 
 from sagemaker.automl.automl import AutoML, AutoMLJob, AutoMLInput  # noqa: F401
 from sagemaker.automl.candidate_estimator import CandidateEstimator, CandidateStep  # noqa: F401
+from sagemaker.automl.automlv2 import (  # noqa: F401
+    AutoMLV2,
+    AutoMLJobV2,
+    LocalAutoMLDataChannel,
+    AutoMLDataChannel,
+    AutoMLTimeSeriesForecastingConfig,
+    AutoMLImageClassificationConfig,
+    AutoMLTabularConfig,
+    AutoMLTextClassificationConfig,
+    AutoMLTextGenerationConfig,
+)
 
 from sagemaker.debugger import ProfilerConfig, Profiler  # noqa: F401
 

src/sagemaker/accept_types.py

@@ -16,6 +16,7 @@
 
 from sagemaker.jumpstart import artifacts, utils as jumpstart_utils
 from sagemaker.jumpstart.constants import DEFAULT_JUMPSTART_SAGEMAKER_SESSION
+from sagemaker.jumpstart.enums import JumpStartModelType
 from sagemaker.session import Session
 
 
@@ -80,6 +81,7 @@ def retrieve_default(
     tolerate_vulnerable_model: bool = False,
     tolerate_deprecated_model: bool = False,
     sagemaker_session: Session = DEFAULT_JUMPSTART_SAGEMAKER_SESSION,
+    model_type: JumpStartModelType = JumpStartModelType.OPEN_WEIGHTS,
 ) -> str:
     """Retrieves the default accept type for the model matching the given arguments.
 
@@ -122,4 +124,5 @@ def retrieve_default(
         tolerate_vulnerable_model=tolerate_vulnerable_model,
         tolerate_deprecated_model=tolerate_deprecated_model,
         sagemaker_session=sagemaker_session,
+        model_type=model_type,
     )