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

Added NP + PD support to parsing for both normal + raw cases #229

Merged
merged 7 commits into from
Jul 3, 2023

Conversation

RobGeada
Copy link
Contributor

@RobGeada RobGeada commented Jun 22, 2023

Refactor Rui's NP+PD PR to enable support for raw parsing as well, as well as fix float type issues.

Resolves: #136

Many thanks for submitting your Pull Request ❤️!

Please make sure that your PR meets the following requirements:

  • You have read the contributors guide
  • Pull Request title is properly formatted: FAI-XYZ Subject
  • Pull Request title contains the target branch if not targeting main: [0.3.x] FAI-XYZ Subject
  • Pull Request contains link to the JIRA issue
  • Pull Request contains link to any dependent or related Pull Request
  • Pull Request contains description of the issue
  • Pull Request does not include fixes for issues other than the main ticket

@RobGeada RobGeada requested a review from a team as a code owner June 22, 2023 15:04
@RobGeada RobGeada requested review from ruivieira and tteofili and removed request for a team June 22, 2023 15:04
@RobGeada
Copy link
Contributor Author

/test trustyai-explainability-e2e

@RobGeada
Copy link
Contributor Author

/retest-required

Copy link
Member

@tteofili tteofili left a comment

Choose a reason for hiding this comment

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

LGTM

.addFp64Contents(values.get(2));

ModelInferResponse.InferOutputTensor outputTensor = ModelInferResponse.InferOutputTensor.newBuilder()
.setDatatype("FP64")
Copy link
Member

Choose a reason for hiding this comment

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

It should be nice to have the possible types in some enum or similar but I don't think we can easily customise these generated classes so let's stay with this for now. We can create a follow up ticket if we agree

Copy link
Member

@ruivieira ruivieira left a comment

Choose a reason for hiding this comment

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

On top of @danielezonca's comments and mine, I think we should add unit tests to the enforced dimensions, eg.

  • fail when dimensions do not match
  • test without hardcoded dimensions
  • test the InferencePayloadReconciler with malformed payloads

@openshift-ci openshift-ci bot added the lgtm label Jun 28, 2023
@openshift-ci openshift-ci bot removed the lgtm label Jun 28, 2023
Copy link
Member

@danielezonca danielezonca left a comment

Choose a reason for hiding this comment

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

/lgtm :)

@openshift-ci
Copy link

openshift-ci bot commented Jun 28, 2023

[APPROVALNOTIFIER] This PR is APPROVED

This pull-request has been approved by: danielezonca, ruivieira, tteofili

The full list of commands accepted by this bot can be found here.

The pull request process is described here

Needs approval from an approver in each of these files:
  • OWNERS [danielezonca,ruivieira,tteofili]

Approvers can indicate their approval by writing /approve in a comment
Approvers can cancel approval by writing /approve cancel in a comment

@openshift-ci openshift-ci bot removed the lgtm label Jun 28, 2023
@openshift-ci
Copy link

openshift-ci bot commented Jun 28, 2023

New changes are detected. LGTM label has been removed.

@RobGeada
Copy link
Contributor Author

/test trustyai-explainability-e2e

@RobGeada
Copy link
Contributor Author

RobGeada commented Jul 3, 2023

/test trustyai-explainability-e2e

@RobGeada RobGeada merged commit 0bdfe07 into trustyai-explainability:main Jul 3, 2023
7 checks passed
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.

None yet

5 participants