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

Automation tests for keras grpc model for triton #1843

Open
wants to merge 8 commits into
base: master
Choose a base branch
from

Conversation

rpancham
Copy link
Contributor

Add support for trition server for keras model format using kserve using gRPC endpoint RHOAIENG-11563

@@ -152,6 +157,51 @@
... AND
... Delete Serving Runtime Template From CLI displayed_name=triton-kserve-grpc

Test KERAS Model Grpc Inference Via UI (Triton on Kserve) # robocop: off=too-long-test-case

Check warning

Code scanning / Robocop

Test case '{{ test_name }}' has too many keywords inside ({{ keyword_count }}/{{ max_allowed_count }}) Warning test

Test case 'Test KERAS Model Grpc Inference Via UI (Triton on Kserve)' has too many keywords inside (24/10)
Copy link
Contributor

github-actions bot commented Sep 20, 2024

Robot Results

✅ Passed ❌ Failed ⏭️ Skipped Total Pass %
546 0 0 546 100

@rpancham rpancham requested review from Raghul-M, bdattoma, jgarciao, tarukumar and lugi0 and removed request for Raghul-M, bdattoma and jgarciao September 23, 2024 07:24
@@ -0,0 +1,63 @@
apiVersion: serving.kserve.io/v1alpha1
Copy link
Contributor

@bdattoma bdattoma Sep 23, 2024

Choose a reason for hiding this comment

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

it seems the same as https://github.com/red-hat-data-services/ods-ci/pull/1844/files
Can we avoid duplication and use one file?

Copy link
Contributor Author

Choose a reason for hiding this comment

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

We are adding this file because to test it on local without those files we cannot test them , once the all PR's are approved we remove the all the duplicate files

Copy link
Contributor

Choose a reason for hiding this comment

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

Then you could use the same filename everytime, so once a PR gets merged you'd just need a rebase. Instead as it is now, you'll need to change all the references to the files in the tests

... aws_access_key=${S3.AWS_ACCESS_KEY_ID} aws_secret_access=${S3.AWS_SECRET_ACCESS_KEY}
... aws_bucket_name=ods-ci-s3
Deploy Kserve Model Via UI model_name=${KERAS_MODEL_NAME} serving_runtime=triton-keras-grpc
... data_connection=model-serving-connection path=tritonkeras/model_repository/ model_framework=tensorflow - 2

Check warning

Code scanning / Robocop

Line is too long ({{ line_length }}/{{ allowed_length }}) Warning test

Line is too long (123/120)
... token=${TRUE}
Wait For Pods To Be Ready label_selector=serving.kserve.io/inferenceservice=${KERAS_MODEL_NAME}
... namespace=${PRJ_TITLE}
${EXPECTED_INFERENCE_GRPC_OUTPUT_KERAS}= Load Json File file_path=${EXPECTED_INFERENCE_GRPC_OUTPUT_FILE_KERAS}

Check warning

Code scanning / Robocop

Line is too long ({{ line_length }}/{{ allowed_length }}) Warning test

Line is too long (122/120)
@rpancham
Copy link
Contributor Author

Verified with Jenkins Build 554

Copy link

sonarcloud bot commented Sep 27, 2024

Copy link
Member

@jiridanek jiridanek left a comment

Choose a reason for hiding this comment

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

I'm not a fan of the way files are not-shared between multiple PRs, but I'm not strictly opposed. Just don't forget to tidy it all up!

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