-
Notifications
You must be signed in to change notification settings - Fork 277
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
base: main
Are you sure you want to change the base?
Conversation
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. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Same comment as for TGI: huggingface/text-generation-inference#3160 (review)
It seems some files are not formatted properly: https://github.com/huggingface/text-embeddings-inference/actions/runs/14595555222/job/40940476819?pr=598
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 |
807ac9b
to
39f005e
Compare
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. |
There was a problem hiding this 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 |
There was a problem hiding this comment.
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?
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.