Merge branch 'master' into ch_integ_tests

Author: malav-shastri

.pylintrc

@@ -310,7 +310,7 @@ ignore-mixin-members=yes
 # (useful for modules/projects where namespaces are manipulated during runtime
 # and thus existing member attributes cannot be deduced by static analysis. It
 # supports qualified module names, as well as Unix pattern matching.
-ignored-modules=distutils
+ignored-modules=
 
 # List of class names for which member attributes should not be checked (useful
 # for classes with dynamically set attributes). This supports the use of

src/sagemaker/huggingface/model.py

@@ -334,11 +334,7 @@ def deploy(
             container_startup_health_check_timeout=container_startup_health_check_timeout,
             inference_recommendation_id=inference_recommendation_id,
             explainer_config=explainer_config,
-            endpoint_logging=kwargs.get("endpoint_logging", False),
-            endpoint_type=kwargs.get("endpoint_type", None),
-            resources=kwargs.get("resources", None),
-            managed_instance_scaling=kwargs.get("managed_instance_scaling", None),
-            routing_config=kwargs.get("routing_config", None),
+            **kwargs,
         )
 
     def register(

src/sagemaker/jumpstart/cache.py

@@ -293,7 +293,8 @@ def _model_id_retrieval_function(
             raise KeyError(error_msg)
 
         error_msg = f"Unable to find model manifest for '{model_id}' with version '{version}'. "
-        error_msg += f"Visit {MODEL_ID_LIST_WEB_URL} for updated list of models. "
+        error_msg += "Specify a different model ID or try a different AWS Region. "
+        error_msg += f"For a list of available models, see {MODEL_ID_LIST_WEB_URL}. "
 
         other_model_id_version = None
         if model_type == JumpStartModelType.OPEN_WEIGHTS:

src/sagemaker/jumpstart/exceptions.py

@@ -32,8 +32,8 @@
 )
 
 INVALID_MODEL_ID_ERROR_MSG = (
-    "Invalid model ID: '{model_id}'. Please visit "
-    f"{MODEL_ID_LIST_WEB_URL} for a list of valid model IDs. "
+    "Invalid model ID: '{model_id}'. Specify a different model ID or try a different AWS Region. "
+    f"For a list of available models, see {MODEL_ID_LIST_WEB_URL}. "
     "The module `sagemaker.jumpstart.notebook_utils` contains utilities for "
     "fetching model IDs. We recommend upgrading to the latest version of sagemaker "
     "to get access to the most models."

src/sagemaker/jumpstart/utils.py

@@ -50,7 +50,12 @@
 )
 from sagemaker.session import Session
 from sagemaker.config import load_sagemaker_config
-from sagemaker.utils import resolve_value_from_config, TagsDict, get_instance_rate_per_hour
+from sagemaker.utils import (
+    resolve_value_from_config,
+    TagsDict,
+    get_instance_rate_per_hour,
+    get_domain_for_region,
+)
 from sagemaker.workflow import is_pipeline_variable
 from sagemaker.user_agent import get_user_agent_extra_suffix
 
@@ -553,7 +558,7 @@ def get_eula_message(model_specs: JumpStartModelSpecs, region: str) -> str:
     return (
         f"Model '{model_specs.model_id}' requires accepting end-user license agreement (EULA). "
         f"See https://{get_jumpstart_content_bucket(region=region)}.s3.{region}."
-        f"amazonaws.com{'.cn' if region.startswith('cn-') else ''}"
+        f"{get_domain_for_region(region)}"
         f"/{model_specs.hosting_eula_key} for terms of use."
     )
 

src/sagemaker/local/image.py

@@ -30,7 +30,6 @@
 import tarfile
 import tempfile
 
-from distutils.spawn import find_executable
 from threading import Thread
 from typing import Dict, List
 from six.moves.urllib.parse import urlparse
@@ -170,7 +169,7 @@ def _get_compose_cmd_prefix():
             compose_cmd_prefix.extend(["docker", "compose"])
             return compose_cmd_prefix
 
-        if find_executable("docker-compose") is not None:
+        if shutil.which("docker-compose") is not None:
             logger.info("'Docker Compose' found using Docker Compose CLI.")
             compose_cmd_prefix.extend(["docker-compose"])
             return compose_cmd_prefix

src/sagemaker/local/utils.py

@@ -21,7 +21,6 @@
 import re
 import errno
 
-from distutils.dir_util import copy_tree
 from six.moves.urllib.parse import urlparse
 
 from sagemaker import s3
@@ -102,7 +101,7 @@ def move_to_destination(source, destination, job_name, sagemaker_session, prefix
 
 
 def recursive_copy(source, destination):
-    """A wrapper around distutils.dir_util.copy_tree.
+    """A wrapper around shutil.copy_tree.
 
     This won't throw any exception when the source directory does not exist.
 
@@ -111,7 +110,7 @@ def recursive_copy(source, destination):
         destination (str): destination path
     """
     if os.path.isdir(source):
-        copy_tree(source, destination)
+        shutil.copytree(source, destination, dirs_exist_ok=True)
 
 
 def kill_child_processes(pid):

src/sagemaker/utils.py

@@ -52,6 +52,15 @@
 from sagemaker.workflow import is_pipeline_variable, is_pipeline_parameter_string
 from sagemaker.workflow.entities import PipelineVariable
 
+ALTERNATE_DOMAINS = {
+    "cn-north-1": "amazonaws.com.cn",
+    "cn-northwest-1": "amazonaws.com.cn",
+    "us-iso-east-1": "c2s.ic.gov",
+    "us-isob-east-1": "sc2s.sgov.gov",
+    "us-isof-south-1": "csp.hci.ic.gov",
+    "us-isof-east-1": "csp.hci.ic.gov",
+}
+
 ECR_URI_PATTERN = r"^(\d+)(\.)dkr(\.)ecr(\.)(.+)(\.)(.*)(/)(.*:.*)$"
 MODEL_PACKAGE_ARN_PATTERN = (
     r"arn:aws([a-z\-]*)?:sagemaker:([a-z0-9\-]*):([0-9]{12}):model-package/(.*)"
@@ -1905,3 +1914,12 @@ def remove_tag_with_key(key: str, tags: Optional[Tags]) -> Optional[Tags]:
     if len(updated_tags) == 1:
         return updated_tags[0]
     return updated_tags
+
+
+def get_domain_for_region(region: str) -> str:
+    """Returns the domain for the given region.
+
+    Args:
+        region (str): AWS region name.
+    """
+    return ALTERNATE_DOMAINS.get(region, "amazonaws.com")

src/sagemaker/workflow/_repack_model.py

@@ -27,13 +27,6 @@
 # is unpacked for inference, the custom entry point will be used.
 # Reference: https://docs.aws.amazon.com/sagemaker/latest/dg/amazon-sagemaker-toolkits.html
 
-# distutils.dir_util.copy_tree works way better than the half-baked
-# shutil.copytree which bombs on previously existing target dirs...
-# alas ... https://bugs.python.org/issue10948
-# we'll go ahead and use the copy_tree function anyways because this
-# repacking is some short-lived hackery, right??
-from distutils.dir_util import copy_tree
-
 from os.path import abspath, realpath, dirname, normpath, join as joinpath
 
 logger = logging.getLogger(__name__)
@@ -188,7 +181,7 @@ def repack(inference_script, model_archive, dependencies=None, source_dir=None):
 
         # copy the "src" dir, which includes the previous training job's model and the
         # custom inference script, to the output of this training job
-        copy_tree(src_dir, "/opt/ml/model")
+        shutil.copytree(src_dir, "/opt/ml/model", dirs_exist_ok=True)
 
 
 if __name__ == "__main__":  # pragma: no cover

src/sagemaker/workflow/_utils.py

@@ -46,7 +46,7 @@
 
 logger = logging.getLogger(__name__)
 
-FRAMEWORK_VERSION = "0.23-1"
+FRAMEWORK_VERSION = "1.2-1"
 INSTANCE_TYPE = "ml.m5.large"
 REPACK_SCRIPT = "_repack_model.py"
 REPACK_SCRIPT_LAUNCHER = "_repack_script_launcher.sh"