Skip to content

Add integration tests for Gaudi #598

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

Open
wants to merge 16 commits into
base: main
Choose a base branch
from

Conversation

baptistecolle
Copy link
Collaborator

What does this PR do?

This PR adds an integration test for Gaudi, with the goal of eventually including it in the CI pipeline. The CI pipeline will be a scheduled nightly test to check that there is no regression in the Gaudi TEI image.

Unfortunately, while working on this, I discovered that TEI is not compatible with Gaudi 1. As a result, it’s currently not possible to enable CI for this test, since we’re still in the process of setting up a CI cluster for Gaudi 2.

This integration test starts a TEI image on HPU, embeds a sample text, and verifies that the resulting embedding matches the expected output.

@baptistecolle baptistecolle requested review from Narsil and regisss April 22, 2025 13:07
@HuggingFaceDocBuilderDev

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.

Copy link
Collaborator

@regisss regisss left a comment

Choose a reason for hiding this comment

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

@baptistecolle
Copy link
Collaborator Author

Thanks, I fixed the linting issue! I converted the PR as a draft until we have the Gaudi 2 and 3 runners for the CI

@baptistecolle baptistecolle marked this pull request as draft April 23, 2025 07:50
@baptistecolle baptistecolle force-pushed the gaudi/add-integration-test branch from 807ac9b to 39f005e Compare June 23, 2025 12:44
@baptistecolle baptistecolle marked this pull request as ready for review June 23, 2025 13:21
@baptistecolle
Copy link
Collaborator Author

I tested the new integration tests for Gaudi on the CI: https://github.com/huggingface/text-embeddings-inference/actions/runs/15825221027/job/44603574014. These tests use the new Gaudi 3 runners.
The goal of this PR is to add CI coverage for Gaudi to ensure that TEI works correctly on this hardware.

@baptistecolle baptistecolle requested a review from regisss June 23, 2025 14:15
Narsil
Narsil previously approved these changes Jun 23, 2025
Copy link
Collaborator

@Narsil Narsil left a comment

Choose a reason for hiding this comment

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

Thanks a lot for this. This LGTM for now. In TEI, we have added some unit tests which might be nice too at some point, but this is already a great starting point.

group: ${{ github.workflow }}-${{ github.job }}-${{ github.head_ref || github.run_id }}
cancel-in-progress: true
runs-on:
group: itac-bm-emr-gaudi3-dell-8gaudi
Copy link
Collaborator

Choose a reason for hiding this comment

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

I think we only need a runner with one device here no?

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.

4 participants