Migration of Pytorch Rest Protocol test on triton for Kserve (UI -> API) #2172
Conversation
![github-advanced-security[bot]](https://avatars.githubusercontent.com/in/57789?s=60&v=4){kind=small}
| @@ -31,6 +31,9 @@ | |||
| ${INFERENCESERVICE_FILEPATH_NEW}= ${LLM_RESOURCES_DIRPATH}/serving_runtimes/isvc | |||
| ${INFERENCESERVICE_FILLED_FILEPATH}= ${INFERENCESERVICE_FILEPATH_NEW}/isvc_filled.yaml | |||
| ${KSERVE_RUNTIME_REST_NAME}= triton-kserve-runtime | |||
| ${PYTORCH_MODEL_NAME}= resnet50 | |||
| ${INFERENCE_REST_INPUT_PYTORCH}= @tests/Resources/Files/triton/kserve-triton-resnet-rest-input.json | |||
| ${EXPECTED_INFERENCE_REST_OUTPUT_FILE__PYTORCH}= tests/Resources/Files/triton/kserve-triton-resnet-rest-output.json | |||
Check warning
Code scanning / Robocop
Line is too long ({{ line_length }}/{{ allowed_length }}) Warning test
| @@ -73,6 +76,47 @@ | |||
| ... AND | |||
| ... Run Keyword If "${KSERVE_MODE}"=="RawDeployment" Terminate Process triton-process kill=true | |||
|
|
|||
| Test Pytorch Model Rest Inference Via API (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
| [Tags] Tier2 RHOAIENG-16912 RunThisTest | ||
| Setup Test Variables model_name=${PYTORCH_MODEL_NAME} use_pvc=${FALSE} use_gpu=${FALSE} | ||
| ... kserve_mode=${KSERVE_MODE} model_path=triton/model_repository/ | ||
| Set Project And Runtime runtime=${KSERVE_RUNTIME_REST_NAME} protocol=${PROTOCOL} namespace=${test_namespace} |
Check warning
Code scanning / Robocop
Line is too long ({{ line_length }}/{{ allowed_length }}) Warning test
| Set Project And Runtime runtime=${KSERVE_RUNTIME_REST_NAME} protocol=${PROTOCOL} namespace=${test_namespace} | ||
| ... download_in_pvc=${DOWNLOAD_IN_PVC} model_name=${PYTORCH_MODEL_NAME} | ||
| ... storage_size=100Mi memory_request=100Mi | ||
| ${requests}= Create Dictionary memory=1Gi |
Check notice
Code scanning / Robocop
{{ create_keyword }} can be replaced with VAR Note test
| END | ||
| ${EXPECTED_INFERENCE_REST_OUTPUT_PYTORCH}= Load Json File | ||
| ... file_path=${EXPECTED_INFERENCE_REST_OUTPUT_FILE_PYTORCH} as_string=${TRUE} | ||
| Verify Model Inference With Retries model_name=${PYTORCH_MODEL_NAME} inference_input=${INFERENCE_REST_INPUT_PYTORCH} |
Check warning
Code scanning / Robocop
Line is too long ({{ line_length }}/{{ allowed_length }}) Warning test
Robot Results
|
|
Verified with Jenkins Build 2284 |
|
| ... isvc_names=${models_names} wait_prj_deletion=${FALSE} kserve_mode=${KSERVE_MODE} | ||
| ... AND | ||
| ... Run Keyword If "${KSERVE_MODE}"=="RawDeployment" Terminate Process triton-process kill=true | ||
|
|
Check warning
Code scanning / Robocop
Trailing whitespace at the end of line Warning test
| [Tags] Tier2 RHOAIENG-16909 | ||
| Setup Test Variables model_name=${PYTORCH_MODEL_NAME} use_pvc=${FALSE} use_gpu=${FALSE} | ||
| ... kserve_mode=${KSERVE_MODE} model_path=triton/model_repository/ | ||
| Set Project And Runtime runtime=${KSERVE_RUNTIME_REST_NAME} protocol=${PROTOCOL} namespace=${test_namespace} |
There was a problem hiding this comment.
@tarukumar @rpancham @Raghul-M @rnetser guys I was thinking..this keyword was designed to use the runtime YAML from ODS-CI repo (iirc at the time the runtime we were using were not in RHOAI yet). Today, if the runtime is already part of the OOTB runtimes maybe it would make more sense to fetch the definition from the cluster itself (i.e., openshift Template objects).
I know the main goal is to move out of ODS-CI for your scrum, but given that these tests are still under maintainance maybe it's worth considering this improvement. Up to you
|
[APPROVALNOTIFIER] This PR is NOT APPROVED This pull-request has been approved by: bdattoma, rpancham, tarukumar The full list of commands accepted by this bot can be found here.
Needs approval from an approver in each of these files:
Approvers can indicate their approval by writing |
tarukumar
merged commit 0b92fee
into
red-hat-data-services:master
No description provided.