forked from aws/sagemaker-python-sdk
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathinstance_types.py
More file actions
153 lines (136 loc) · 6.85 KB
/
instance_types.py
File metadata and controls
153 lines (136 loc) · 6.85 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
# Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License"). You
# may not use this file except in compliance with the License. A copy of
# the License is located at
#
# http://aws.amazon.com/apache2.0/
#
# or in the "license" file accompanying this file. This file is
# distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF
# ANY KIND, either express or implied. See the License for the specific
# language governing permissions and limitations under the License.
"""Accessors to retrieve instance types."""
from __future__ import absolute_import
import logging
from typing import List, Optional
from sagemaker.jumpstart import utils as jumpstart_utils
from sagemaker.jumpstart import artifacts
from sagemaker.jumpstart.constants import DEFAULT_JUMPSTART_SAGEMAKER_SESSION
from sagemaker.jumpstart.enums import JumpStartModelType
from sagemaker.session import Session
logger = logging.getLogger(__name__)
def retrieve_default(
region: Optional[str] = None,
model_id: Optional[str] = None,
model_version: Optional[str] = None,
scope: Optional[str] = None,
tolerate_vulnerable_model: bool = False,
tolerate_deprecated_model: bool = False,
sagemaker_session: Session = DEFAULT_JUMPSTART_SAGEMAKER_SESSION,
training_instance_type: Optional[str] = None,
model_type: JumpStartModelType = JumpStartModelType.OPEN_WEIGHTS,
) -> str:
"""Retrieves the default instance type for the model matching the given arguments.
Args:
region (str): The AWS Region for which to retrieve the default instance type.
Defaults to ``None``.
model_id (str): The model ID of the model for which to
retrieve the default instance type. (Default: None).
model_version (str): The version of the model for which to retrieve the
default instance type. (Default: None).
scope (str): The model type, i.e. what it is used for.
Valid values: "training" and "inference".
tolerate_vulnerable_model (bool): True if vulnerable versions of model
specifications should be tolerated (exception not raised). If False, raises an
exception if the script used by this version of the model has dependencies with known
security vulnerabilities. (Default: False).
tolerate_deprecated_model (bool): True if deprecated models should be tolerated
(exception not raised). False if these models should raise an exception.
(Default: False).
sagemaker_session (sagemaker.session.Session): A SageMaker Session
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).
training_instance_type (str): In the case of a model fine-tuned on SageMaker, the training
instance type used for the training job that produced the fine-tuned weights.
Optionally supply this to get a inference instance type conditioned
on the training instance, to ensure compatability of training artifact to inference
instance. (Default: None).
Returns:
str: The default instance type to use for the model.
Raises:
ValueError: If the combination of arguments specified is not supported.
"""
if not jumpstart_utils.is_jumpstart_model_input(model_id, model_version):
raise ValueError(
"Must specify JumpStart `model_id` and `model_version` when retrieving instance types."
)
if scope is None:
raise ValueError("Must specify scope for instance types.")
return artifacts._retrieve_default_instance_type(
model_id,
model_version,
scope,
region,
tolerate_vulnerable_model,
tolerate_deprecated_model,
sagemaker_session=sagemaker_session,
training_instance_type=training_instance_type,
model_type=model_type,
)
def retrieve(
region: Optional[str] = None,
model_id: Optional[str] = None,
model_version: Optional[str] = None,
scope: Optional[str] = None,
tolerate_vulnerable_model: bool = False,
tolerate_deprecated_model: bool = False,
sagemaker_session: Session = DEFAULT_JUMPSTART_SAGEMAKER_SESSION,
training_instance_type: Optional[str] = None,
) -> List[str]:
"""Retrieves the supported training instance types for the model matching the given arguments.
Args:
region (str): The AWS Region for which to retrieve the supported instance types.
Defaults to ``None``.
model_id (str): The model ID of the model for which to
retrieve the supported instance types. (Default: None).
model_version (str): The version of the model for which to retrieve the
supported instance types. (Default: None).
tolerate_vulnerable_model (bool): True if vulnerable versions of model
specifications should be tolerated (exception not raised). If False, raises an
exception if the script used by this version of the model has dependencies with known
security vulnerabilities. (Default: False).
tolerate_deprecated_model (bool): True if deprecated models should be tolerated
(exception not raised). False if these models should raise an exception.
(Default: False).
sagemaker_session (sagemaker.session.Session): A SageMaker Session
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).
training_instance_type (str): In the case of a model fine-tuned on SageMaker, the training
instance type used for the training job that produced the fine-tuned weights.
Optionally supply this to get a inference instance type conditioned
on the training instance, to ensure compatability of training artifact to inference
instance. (Default: None).
Returns:
list: The supported instance types to use for the model.
Raises:
ValueError: If the combination of arguments specified is not supported.
"""
if not jumpstart_utils.is_jumpstart_model_input(model_id, model_version):
raise ValueError(
"Must specify JumpStart `model_id` and `model_version` when retrieving instance types."
)
if scope is None:
raise ValueError("Must specify scope for instance types.")
return artifacts._retrieve_instance_types(
model_id,
model_version,
scope,
region,
tolerate_vulnerable_model,
tolerate_deprecated_model,
sagemaker_session=sagemaker_session,
training_instance_type=training_instance_type,
)