Automation tests for keras rest model for triton #1841
Conversation
![github-advanced-security[bot]](https://avatars.githubusercontent.com/in/57789?s=60&v=4){kind=small}
...odel_serving/1009__model_serving_triton_on_kserve/1009__model_serving_triton_on_kserve.robot
Fixed
Show fixed
Hide fixed
...odel_serving/1009__model_serving_triton_on_kserve/1009__model_serving_triton_on_kserve.robot
Fixed
Show fixed
Hide fixed
...odel_serving/1009__model_serving_triton_on_kserve/1009__model_serving_triton_on_kserve.robot
Fixed
Show fixed
Hide fixed
...odel_serving/1009__model_serving_triton_on_kserve/1009__model_serving_triton_on_kserve.robot
Fixed
Show fixed
Hide fixed
Robot Results
|
| @@ -152,6 +157,37 @@ | |||
| ... AND | |||
| ... Delete Serving Runtime Template From CLI displayed_name=triton-kserve-grpc | |||
|
|
|||
| Test KERAS Model Inference Via UI(Triton on Kserve) | |||
Check warning
Code scanning / Robocop
Test case '{{ test_name }}' is too long ({{ test_length }}/{{ allowed_length }}) Warning test
| @@ -152,6 +157,37 @@ | |||
| ... AND | |||
| ... Delete Serving Runtime Template From CLI displayed_name=triton-kserve-grpc | |||
|
|
|||
| Test KERAS Model Inference Via UI(Triton on Kserve) | |||
Check warning
Code scanning / Robocop
Test case '{{ test_name }}' has too many keywords inside ({{ keyword_count }}/{{ max_allowed_count }}) Warning test
| @@ -0,0 +1,55 @@ | |||
| apiVersion: serving.kserve.io/v1alpha1 | |||
There was a problem hiding this comment.
this one seems the same as https://github.com/red-hat-data-services/ods-ci/pull/1846/files.
Is it possible to avoid the duplication and use one single file?
There was a problem hiding this comment.
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
There was a problem hiding this comment.
then you can just merge one PR with the file you need and then rebase the dependent one
ods_ci/tests/Resources/OCP.resource
Outdated
| @@ -108,7 +108,7 @@ Get Events And Pod Logs | |||
|
|
|||
| Wait For Pods To Be Ready | |||
| [Arguments] ${label_selector} ${namespace} ${timeout}=600s ${exp_replicas}=${NONE} | |||
| Wait Until Keyword Succeeds ${timeout} 3s | |||
| Wait Until Keyword Succeeds ${timeout} 15s | |||
There was a problem hiding this comment.
better to parametrize it. The retry depends on the timeout as well, this may impact other test cases
rpancham
force-pushed
the
keras_rest
branch
from
3ea6a86
to
75f7b2e
Compare
rpancham
force-pushed
the
keras_rest
branch
from
121bc4f
to
7e329f1
Compare
| ... aws_access_key=${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-rest | ||
| ... 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
|
Verified with Jenkins Build 555 |
|
| ... Clean All Models Of Current User | ||
| ... AND | ||
| ... Delete Serving Runtime Template From CLI displayed_name=triton-keras-rest | ||
|
|
Check warning
Code scanning / Robocop
Invalid number of empty lines between sections ({{ empty_lines }}/{{ allowed_empty_lines }}) Warning test
Add support for trition server for keras model format using kserve using REST endpoint RHOAIENG-11563