Skip to content

Conversation

@malte-aws
Copy link
Contributor

Issue #, if available: #3

Description of changes:

  • updates enable docker access on SageMaker Studio domain utility function to make clear that is only runs if local_mode is set
  • adds additional comments for documentation
  • updates ECR respository name to include sagemaker in name to prevent insufficient IAM permissions with AmazonSageMakerFullAccess managed policy Use an ECR repo name containing sagemaker for streamlined IAM #3

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

@malte-aws malte-aws self-assigned this Aug 4, 2025
@malte-aws malte-aws requested a review from athewsey August 4, 2025 08:31
"outputs": [],
"source": [
"use_local_mode = True # Set to true to run on local instance\n",
"use_local_mode = False # Set to true to run on local instance\n",
Copy link

Choose a reason for hiding this comment

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

Just wanted to check, this is an intentional change to the default behaviour - not an accidental check-in, right?

Comment on lines -625 to +662
" # use_spot_instances=True, # Cost efficient inference. Inference can be restarted if no spot capacity. \n",
" # use_spot_instances=True, # Enable cost efficient inference. Inference can be restarted if no spot capacity. \n",
Copy link

Choose a reason for hiding this comment

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

It's not a problem, but I wonder if there was a particular reason we have spot enabled by default in training but disabled by default in inference?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants