Merge branch 'master' of github.com:rvasahu-amazon/sagemaker-python-sdk

Author: rvasahu-amazon

CHANGELOG.md

@@ -1,5 +1,42 @@
 # Changelog
 
+## v2.200.0 (2023-12-13)
+
+### Deprecations and Removals
+
+ * remove explicit `partitions` key requirement on pysdk side.
+
+### Features
+
+ * add non-repeating config logger
+ * Add SageMaker Geospatial verison 1.x images
+ * TGI 1.2.0 Image Uri
+ * support model.register() with triton model
+ * Enable retrieving function step results for local mode
+
+### Bug Fixes and Other Changes
+
+ * TGI 1.3.1
+ * excessive jumpstart instance type logging
+ * Support local mode for remote function
+ * `Session.download_data` can not download nested objects
+ * Fix writing into non-closed file with git clone command
+ * mitigation of xgboost container incompatibility with new version
+ * update image and hardware validation with inf and graviton
+ * remove two setuptools deprecations
+ * minor jumpstart dev ex improvements
+ * save utils fix
+ * Correct DJL neuronx regions
+ * delete unused file inference-experience-dev-tester.sh
+ * Fix Experiment Run integ test w.r.t unexpected boto3 version
+ * Bump test dependencies versions
+ * fast follow on js uncompressed support - ModelBuilder
+ * Modify Region List for Neuron Images (HF neuron/neuronx, PT Neuron)
+
+### Documentation Changes
+
+ * Mention for custom Docker Image
+
 ## v2.199.0 (2023-11-30)
 
 ### Features

VERSION

@@ -1 +1 @@
-2.199.1.dev0
+2.200.1.dev0

src/sagemaker/config/config.py

@@ -28,9 +28,10 @@
 from botocore.utils import merge_dicts
 from six.moves.urllib.parse import urlparse
 from sagemaker.config.config_schema import SAGEMAKER_PYTHON_SDK_CONFIG_SCHEMA
-from sagemaker.config.config_utils import get_sagemaker_config_logger
+from sagemaker.config.config_utils import non_repeating_log_factory, get_sagemaker_config_logger
 
 logger = get_sagemaker_config_logger()
+log_info_function = non_repeating_log_factory(logger, "info")
 
 _APP_NAME = "sagemaker"
 # The default name of the config file.
@@ -52,7 +53,9 @@
 S3_PREFIX = "s3://"
 
 
-def load_sagemaker_config(additional_config_paths: List[str] = None, s3_resource=None) -> dict:
+def load_sagemaker_config(
+    additional_config_paths: List[str] = None, s3_resource=None, repeat_log=False
+) -> dict:
     """Loads config files and merges them.
 
     By default, this method first searches for config files in the default locations
@@ -99,6 +102,8 @@ def load_sagemaker_config(additional_config_paths: List[str] = None, s3_resource
             <https://boto3.amazonaws.com/v1/documentation/api\
             /latest/reference/core/session.html#boto3.session.Session.resource>`__.
             This argument is not needed if the config files are present in the local file system.
+        repeat_log (bool): Whether the log with the same contents should be emitted.
+            Default to ``False``
     """
     default_config_path = os.getenv(
         ENV_VARIABLE_ADMIN_CONFIG_OVERRIDE, _DEFAULT_ADMIN_CONFIG_FILE_PATH
@@ -109,6 +114,11 @@ def load_sagemaker_config(additional_config_paths: List[str] = None, s3_resource
         config_paths += additional_config_paths
     config_paths = list(filter(lambda item: item is not None, config_paths))
     merged_config = {}
+
+    log_info = log_info_function
+    if repeat_log:
+        log_info = logger.info
+
     for file_path in config_paths:
         config_from_file = {}
         if file_path.startswith(S3_PREFIX):
@@ -130,9 +140,9 @@ def load_sagemaker_config(additional_config_paths: List[str] = None, s3_resource
         if config_from_file:
             validate_sagemaker_config(config_from_file)
             merge_dicts(merged_config, config_from_file)
-            logger.info("Fetched defaults config from location: %s", file_path)
+            log_info("Fetched defaults config from location: %s", file_path)
         else:
-            logger.info("Not applying SDK defaults from location: %s", file_path)
+            log_info("Not applying SDK defaults from location: %s", file_path)
 
     return merged_config
 

src/sagemaker/config/config_utils.py

@@ -15,9 +15,11 @@
 These utils may be used inside or outside the config module.
 """
 from __future__ import absolute_import
+from collections import deque
 
 import logging
 import sys
+from typing import Callable
 
 
 def get_sagemaker_config_logger():
@@ -197,3 +199,33 @@ def _log_sagemaker_config_merge(
     else:
         # nothing was specified in the config and nothing is being automatically applied
         logger.debug("Skipped value because no value defined\n  config key = %s", config_key_path)
+
+
+def non_repeating_log_factory(logger: logging.Logger, method: str, cache_size=100) -> Callable:
+    """Create log function that filters the repeated messages.
+
+    By default. It only keeps track of last 100 messages, if a repeated
+    message arrives after the ``cache_size`` messages, it will be displayed.
+
+    Args:
+        logger (logging.Logger): the logger to be used to dispatch the message.
+        method (str): the log method, can be info, warning or debug.
+        cache_size (int): the number of last log messages to keep in cache.
+            Default to 100
+
+    Returns:
+        (Callable): the new log method
+    """
+    if method not in ["info", "warning", "debug"]:
+        raise ValueError("Not supported logging method.")
+
+    _caches = deque(maxlen=cache_size)
+    log_method = getattr(logger, method)
+
+    def new_log_method(msg, *args, **kwargs):
+        key = f"{msg}:{args}"
+        if key not in _caches:
+            log_method(msg, *args, **kwargs)
+            _caches.append(key)
+
+    return new_log_method

src/sagemaker/git_utils.py

@@ -14,6 +14,7 @@
 from __future__ import absolute_import
 
 import os
+from pathlib import Path
 import subprocess
 import tempfile
 import warnings
@@ -279,11 +280,13 @@ def _run_clone_command(repo_url, dest_dir):
         subprocess.check_call(["git", "clone", repo_url, dest_dir], env=my_env)
     elif repo_url.startswith("git@") or repo_url.startswith("ssh://"):
         try:
-            with tempfile.NamedTemporaryFile() as sshnoprompt:
-                with open(sshnoprompt.name, "w") as write_pipe:
-                    write_pipe.write("ssh -oBatchMode=yes $@")
-                os.chmod(sshnoprompt.name, 0o511)
-                my_env["GIT_SSH"] = sshnoprompt.name
+            with tempfile.TemporaryDirectory() as tmp_dir:
+                custom_ssh_executable = Path(tmp_dir) / "ssh_batch"
+                with open(custom_ssh_executable, "w") as pipe:
+                    print("#!/bin/sh", file=pipe)
+                    print("ssh -oBatchMode=yes $@", file=pipe)
+                os.chmod(custom_ssh_executable, 0o511)
+                my_env["GIT_SSH"] = str(custom_ssh_executable)
                 subprocess.check_call(["git", "clone", repo_url, dest_dir], env=my_env)
         except subprocess.CalledProcessError:
             del my_env["GIT_SSH"]

src/sagemaker/image_uri_config/huggingface-llm.json

@@ -6,7 +6,9 @@
             "0.8": "0.8.2",
             "0.9": "0.9.3",
             "1.0": "1.0.3",
-            "1.1": "1.1.0"
+            "1.1": "1.1.0",
+            "1.2": "1.2.0",
+            "1.3": "1.3.1"
         },
         "versions": {
             "0.6.0": {
@@ -260,6 +262,48 @@
                 "tag_prefix": "2.1.1-tgi1.2.0",
                 "repository": "huggingface-pytorch-tgi-inference",
                 "container_version": {"gpu": "cu121-ubuntu20.04"}
+            },
+            "1.3.1": {
+                "py_versions": ["py310"],
+                "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-south-2": "772153158452",
+                    "ap-southeast-1": "763104351884",
+                    "ap-southeast-2": "763104351884",
+                    "ap-southeast-3": "907027046896",
+                    "ap-southeast-4": "457447274322",
+                    "ca-central-1": "763104351884",
+                    "cn-north-1": "727897471807",
+                    "cn-northwest-1": "727897471807",
+                    "eu-central-1": "763104351884",
+                    "eu-central-2": "380420809688",
+                    "eu-north-1": "763104351884",
+                    "eu-west-1": "763104351884",
+                    "eu-west-2": "763104351884",
+                    "eu-west-3": "763104351884",
+                    "eu-south-1": "692866216735",
+                    "eu-south-2": "503227376785",
+                    "me-south-1": "217643126080",
+                    "me-central-1": "914824155844",
+                    "sa-east-1": "763104351884",
+                    "us-east-1": "763104351884",
+                    "us-east-2": "763104351884",
+                    "us-gov-east-1": "446045086412",
+                    "us-gov-west-1": "442386744353",
+                    "us-iso-east-1": "886529160074",
+                    "us-isob-east-1": "094389454867",
+                    "us-west-1": "763104351884",
+                    "us-west-2": "763104351884"
+                },
+                "tag_prefix": "2.1.1-tgi1.3.1",
+                "repository": "huggingface-pytorch-tgi-inference",
+                "container_version": {"gpu": "cu121-ubuntu20.04"}
             }
         }
     }

src/sagemaker/jumpstart/factory/estimator.py

@@ -336,6 +336,7 @@ def get_deploy_kwargs(
         tolerate_vulnerable_model=tolerate_vulnerable_model,
         tolerate_deprecated_model=tolerate_deprecated_model,
         training_instance_type=training_instance_type,
+        disable_instance_type_logging=True,
     )
 
     estimator_deploy_kwargs: JumpStartEstimatorDeployKwargs = JumpStartEstimatorDeployKwargs(

src/sagemaker/jumpstart/factory/model.py

@@ -171,7 +171,9 @@ def _add_vulnerable_and_deprecated_status_to_kwargs(
     return kwargs
 
 
-def _add_instance_type_to_kwargs(kwargs: JumpStartModelInitKwargs) -> JumpStartModelInitKwargs:
+def _add_instance_type_to_kwargs(
+    kwargs: JumpStartModelInitKwargs, disable_instance_type_logging: bool = False
+) -> JumpStartModelInitKwargs:
     """Sets instance type based on default or override, returns full kwargs."""
 
     orig_instance_type = kwargs.instance_type
@@ -187,7 +189,7 @@ def _add_instance_type_to_kwargs(kwargs: JumpStartModelInitKwargs) -> JumpStartM
         training_instance_type=kwargs.training_instance_type,
     )
 
-    if orig_instance_type is None:
+    if not disable_instance_type_logging and orig_instance_type is None:
         JUMPSTART_LOGGER.info(
             "No instance type selected for inference hosting endpoint. Defaulting to %s.",
             kwargs.instance_type,
@@ -551,9 +553,7 @@ def get_deploy_kwargs(
 
     deploy_kwargs = _add_endpoint_name_to_kwargs(kwargs=deploy_kwargs)
 
-    deploy_kwargs = _add_instance_type_to_kwargs(
-        kwargs=deploy_kwargs,
-    )
+    deploy_kwargs = _add_instance_type_to_kwargs(kwargs=deploy_kwargs)
 
     deploy_kwargs.initial_instance_count = initial_instance_count or 1
 
@@ -677,6 +677,7 @@ def get_init_kwargs(
     git_config: Optional[Dict[str, str]] = None,
     model_package_arn: Optional[str] = None,
     training_instance_type: Optional[str] = None,
+    disable_instance_type_logging: bool = False,
     resources: Optional[ResourceRequirements] = None,
 ) -> JumpStartModelInitKwargs:
     """Returns kwargs required to instantiate `sagemaker.estimator.Model` object."""
@@ -720,7 +721,7 @@ def get_init_kwargs(
     model_init_kwargs = _add_model_name_to_kwargs(kwargs=model_init_kwargs)
 
     model_init_kwargs = _add_instance_type_to_kwargs(
-        kwargs=model_init_kwargs,
+        kwargs=model_init_kwargs, disable_instance_type_logging=disable_instance_type_logging
     )
 
     model_init_kwargs = _add_image_uri_to_kwargs(kwargs=model_init_kwargs)

src/sagemaker/model.py

@@ -866,16 +866,10 @@ def _create_sagemaker_model(
                 # _base_name, model_name are not needed under PipelineSession.
                 # the model_data may be Pipeline variable
                 # which may break the _base_name generation
-                model_uri = None
-                if isinstance(self.model_data, (str, PipelineVariable)):
-                    model_uri = self.model_data
-                elif isinstance(self.model_data, dict):
-                    model_uri = self.model_data.get("S3DataSource", {}).get("S3Uri", None)
-
                 self._ensure_base_name_if_needed(
                     image_uri=container_def["Image"],
                     script_uri=self.source_dir,
-                    model_uri=model_uri,
+                    model_uri=self._get_model_uri(),
                 )
                 self._set_model_name_if_needed()
 
@@ -912,6 +906,14 @@ def _create_sagemaker_model(
             )
             self.sagemaker_session.create_model(**create_model_args)
 
+    def _get_model_uri(self):
+        model_uri = None
+        if isinstance(self.model_data, (str, PipelineVariable)):
+            model_uri = self.model_data
+        elif isinstance(self.model_data, dict):
+            model_uri = self.model_data.get("S3DataSource", {}).get("S3Uri", None)
+        return model_uri
+
     def _ensure_base_name_if_needed(self, image_uri, script_uri, model_uri):
         """Create a base name from the image URI if there is no model name provided.
 
@@ -1496,7 +1498,7 @@ def deploy(
             self._ensure_base_name_if_needed(
                 image_uri=self.image_uri,
                 script_uri=self.source_dir,
-                model_uri=self.model_data,
+                model_uri=self._get_model_uri(),
             )
             if self._base_name is not None:
                 self._base_name = "-".join((self._base_name, compiled_model_suffix))

src/sagemaker/remote_function/job.py

@@ -891,7 +891,7 @@ def wait(self, timeout: int = None):
         """
 
         self._last_describe_response = _logs_for_job(
-            boto_session=self.sagemaker_session.boto_session,
+            sagemaker_session=self.sagemaker_session,
             job_name=self.job_name,
             wait=True,
             timeout=timeout,