Skip to content

WIP: Single endpoint per stage #242

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 3 commits into from
Nov 16, 2023
Merged

WIP: Single endpoint per stage #242

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
43464ac
decouple version and stage name
daavoo Aug 28, 2023
9d9c401
bump versions
daavoo Aug 28, 2023
ca4bbd0
merge and fix
Nov 3, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
24 changes: 15 additions & 9 deletions example-get-started-experiments/code/sagemaker/deploy_model.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,6 +3,7 @@
import sys

import boto3
import botocore

from sagemaker.deserializers import JSONDeserializer
from sagemaker.pytorch import PyTorchModel
Expand Down Expand Up @@ -34,16 +35,11 @@ def deploy(
sagemaker_logger.setLevel(logging.DEBUG)
sagemaker_logger.addHandler(logging.StreamHandler(sys.stdout))

composed_name = re.sub(
r"[^a-zA-Z0-9\-]", "-", f"{name}-{version}-{stage}")

try:
boto3.client("sagemaker").delete_endpoint(EndpointName=composed_name)
except:
pass
version_name = re.sub(
r"[^a-zA-Z0-9\-]", "-", f"{name}-{version}")

model = PyTorchModel(
name=composed_name,
name=version_name,
model_data=model_data,
framework_version="1.12",
py_version="py38",
Expand All @@ -57,11 +53,21 @@ def deploy(
},
)

stage_name = re.sub(
r"[^a-zA-Z0-9\-]", "-", f"{name}-{stage}")
try:
boto3.client("sagemaker").delete_endpoint(EndpointName=stage_name)
except botocore.exceptions.ClientError as e:
sagemaker_logger.warn(e)
try:
boto3.client("sagemaker").delete_endpoint_config(EndpointConfigName=stage_name)
except botocore.exceptions.ClientError as e:
sagemaker_logger.warn(e)

return model.deploy(
initial_instance_count=1,
deserializer=JSONDeserializer(),
endpoint_name=composed_name,
endpoint_name=stage_name,
serverless_inference_config=ServerlessInferenceConfig(
memory_size_in_mb=memory_size[stage],
max_concurrency=max_concurrency[stage]
Expand Down