Skip to content

fix: Enable S3 Upload on local container -> sagemaker endpoint overwrite for TGI, TEI, MMS #4814

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

Merged
merged 1 commit into from
Aug 2, 2024

Conversation

gwang111
Copy link
Collaborator

@gwang111 gwang111 commented Jul 31, 2024

Issue #, if available: N/A

Description of changes:

  1. For TGI, TEI, Transformers builder, if not optimized & if overwritting, upload the model artifacts to customer's S3 location
  2. Prune deprecated TRANSFORMERS_CACHE env var from the builder code
  3. Switch deprecated TRANSFORMERS_OFFLINE env var to HF_HUB_OFFLINE env var

Testing done:

  1. Add UT coverage for TGI, TEI, Transformers builder to verify that on overwrite to SAGEMAKER_ENDPOINT mode that S3 upload is set to True
  2. Add UT coverage for TGI, TEI, Transformers builder to verify that when going DIRECTLY to SAGEMAKER_ENDPOINT mode that S3 upload is not enabled
  3. Add UT coverage for TGI, TEI, Transformers builder to verify that when the model has been optimized that S3 upload is not enabled
  4. Add new UT suite for TGI

Verifications:

TGI:

  • Verify overwrite
    image

TEI

  • Verify overwrite
    image

MMS

  • Verify overwrite
    image

Verify no regressions in Optimize

image

Merge Checklist

Put an x in the boxes that apply. You can also fill these out after creating the PR. If you're unsure about any of them, don't hesitate to ask. We're here to help! This is simply a reminder of what we are going to look for before merging your pull request.

General

  • I have read the CONTRIBUTING doc
  • I certify that the changes I am introducing will be backward compatible, and I have discussed concerns about this, if any, with the Python SDK team
  • I used the commit message format described in CONTRIBUTING
  • I have passed the region in to all S3 and STS clients that I've initialized as part of this change.
  • I have updated any necessary documentation, including READMEs and API docs (if appropriate)

Tests

  • I have added tests that prove my fix is effective or that my feature works (if appropriate)
  • I have added unit and/or integration tests as appropriate to ensure backward compatibility of the changes
  • I have checked that my tests are not configured for a specific region or account (if appropriate)
  • I have used unique_name_from_base to create resource names in integ tests (if appropriate)

By submitting this pull request, I confirm that my contribution is made under the terms of the Apache 2.0 license.

@gwang111 gwang111 requested a review from a team as a code owner July 31, 2024 18:24
@gwang111 gwang111 requested review from mohanasudhan and removed request for mohanasudhan July 31, 2024 18:24
@samruds samruds removed their request for review August 1, 2024 18:03
…NDPOINT overwrite for TGI, TEI, MMS model servers
@gwang111 gwang111 changed the title [Fix] Enable S3 Upload on local container -> sagemaker endpoint overwrite for TGI, TEI, MMS fix: Enable S3 Upload on local container -> sagemaker endpoint overwrite for TGI, TEI, MMS Aug 2, 2024
@nargokul nargokul merged commit ee6ef13 into aws:master Aug 2, 2024
14 checks passed
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.

5 participants