Skip to content
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.

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

feat(construct): SageMaker model deployment construct #95

Merged
merged 24 commits into from
Nov 14, 2023

Conversation

krokoko
Copy link
Collaborator

@krokoko krokoko commented Nov 14, 2023

Fixes #

  • Add construct developed by @spugachev to deploy models from Jumpstart/Hugging face to an amazon sagemaker endpoint
  • Add tests and readme
  • Tested through a lambda function for request/response, deployed both a model from Jumpstart and one from hugging face

By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of the project license.

Copy link
Contributor

@justintlewis justintlewis left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Some minor grammar issues in the docs.


import { Construct } from 'constructs';
import { Stack, StackProps, Aws } from 'aws-cdk-lib';
import { JumpStartSageMakerEndpoint, JumpStartModel, SageMakerInstanceType, HuggingFaceSageMakerEndpoint, DeepLearningContainerImage } from '@awslabs/generative-ai-cdk-constructs';
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@awslabs would be replaced by @cdk-lib in public repository.

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

yes :) will update the PR branch when this is merged

console.log(repositoryName);

const pageSize = 1000;
const hostname = '763104351884.dkr.ecr.us-west-2.amazonaws.com';
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

const hostname = '763104351884.dkr.ecr.us-west-2.amazonaws.com';

Are hardcoded registry and region required here?

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This value is used to get the list of available DLC images (https://github.com/aws/deep-learning-containers/blob/master/available_images.md)

dineshSajwan
dineshSajwan previously approved these changes Nov 14, 2023
Copy link
Contributor

@justintlewis justintlewis left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Minor language changes to properly reflect the type of models that can be deployed.

README.md Outdated Show resolved Hide resolved
README.md Outdated Show resolved Hide resolved
@krokoko krokoko merged commit f383bc2 into main Nov 14, 2023
8 checks passed
@krokoko krokoko deleted the aws-sagemaker-model-deployment branch November 14, 2023 17:30
@justintlewis justintlewis removed the request for review from spugachev November 14, 2023 17:30
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging this pull request may close these issues.

6 participants