Backport of Added Tensorflow model REST protocol test on triton for Kserve (#1846) #2113
Conversation
![github-advanced-security[bot]](https://avatars.githubusercontent.com/in/57789?s=60&v=4){kind=small}
| @@ -292,14 +292,18 @@ | |||
| ... set to ${TRUE}. | |||
| [Arguments] ${model_name} ${inference_input} ${token_auth}=${FALSE} ${project_title}=${NONE} | |||
| ... ${kserve_mode}=Serverless ${deployment_mode}=UI ${service_port}=8888 ${end_point}=${NONE} | |||
| ... ${service_account_name}=default-name ${token}=${NONE} | |||
| ... ${service_account_name}=default-name ${token}=${NONE} ${set_json_content_type}=${FALSE} | |||
Check notice
Code scanning / Robocop
There is too many arguments per continuation line ({{ arguments_count }} / {{ max_arguments_count }}) Note test
| @@ -355,15 +362,15 @@ | |||
| [Documentation] Verifies that the inference result of a model is equal to an expected output | |||
| [Arguments] ${model_name} ${inference_input} ${expected_inference_output} ${token_auth}=${FALSE} | |||
| ... ${project_title}=${NONE} ${deployment_mode}=UI ${kserve_mode}=Serverless | |||
| ... ${service_port}=${NONE} ${end_point}=${NONE} ${token}=${NONE} | |||
| ... ${service_port}=${NONE} ${end_point}=${NONE} ${token}=${NONE} ${set_json_content_type}=${FALSE} | |||
Check notice
Code scanning / Robocop
There is too many arguments per continuation line ({{ arguments_count }} / {{ max_arguments_count }}) Note test
| @@ -385,9 +392,10 @@ | |||
| ... This is a temporary mitigation meanwhile we find a better way to check the model | |||
| [Arguments] ${model_name} ${inference_input} ${expected_inference_output} ${token_auth}=${FALSE} | |||
| ... ${project_title}=${NONE} ${retries}=${5} ${deployment_mode}=UI ${kserve_mode}=Serverless | |||
| ... ${service_port}=${NONE} ${end_point}=${NONE} | |||
| ... ${service_port}=${NONE} ${end_point}=${NONE} ${set_json_content_type}=${FALSE} | |||
Check notice
Code scanning / Robocop
There is too many arguments per continuation line ({{ arguments_count }} / {{ max_arguments_count }}) Note test
| @@ -398,7 +406,7 @@ | |||
| ${status}= Run Keyword And Return Status Verify Model Inference | |||
| ... ${model_name} ${inference_input} ${expected_inference_output} ${token_auth} | |||
| ... project_title=${project_title} deployment_mode=${deployment_mode} kserve_mode=${kserve_mode} | |||
| ... service_port=${service_port} end_point=${end_point} | |||
| ... service_port=${service_port} end_point=${end_point} set_json_content_type=${set_json_content_type} | |||
Check warning
Code scanning / Robocop
Line is too long ({{ line_length }}/{{ allowed_length }}) Warning test
| ${PYTORCH_RUNTIME_NAME}= triton-kserve-rest | ||
| ${PYTORCH_RUNTIME_FILEPATH}= ${RESOURCES_DIRPATH}/triton_onnx_rest_servingruntime.yaml | ||
| ${EXPECTED_INFERENCE_REST_OUTPUT_FILE_PYTORCH}= tests/Resources/Files/triton/kserve-triton-resnet-rest-output.json | ||
| ${INFERENCE_REST_INPUT_TENSORFLOW}= @tests/Resources/Files/triton/kserve-triton-tensorflow-rest-input.json | ||
| ${TENSORFLOW_RUNTIME_FILEPATH}= ${RESOURCES_DIRPATH}/triton_tensorflow_rest_servingruntime.yaml | ||
| ${EXPECTED_INFERENCE_REST_OUTPUT_FILE_TENSORFLOW}= tests/Resources/Files/triton/kserve-triton-tensorflow-rest-output.json |
Check warning
Code scanning / Robocop
Line is too long ({{ line_length }}/{{ allowed_length }}) Warning test
| ... existing_project=${FALSE} | ||
| Open Dashboard Settings settings_page=Serving runtimes | ||
| Upload Serving Runtime Template runtime_filepath=${ONNX_GRPC_RUNTIME_FILEPATH} | ||
| ... serving_platform=single runtime_protocol=gRPC |
Check warning
Code scanning / Robocop
Test case '{{ test_name }}' has too many keywords inside ({{ keyword_count }}/{{ max_allowed_count }}) Warning test
| ... AND | ||
| ... Delete Serving Runtime Template From CLI displayed_name=triton-kserve-grpc | ||
|
|
||
| Test Tensorflow Model Rest Inference Via UI (Triton on Kserve) # robocop: off=too-long-test-case |
Check notice
Code scanning / Robocop
Variable '{{ name }}' is assigned but not used Note test
| ... AND | ||
| ... Delete Serving Runtime Template From CLI displayed_name=triton-kserve-grpc | ||
|
|
||
| Test Tensorflow Model Rest Inference Via UI (Triton on Kserve) # robocop: off=too-long-test-case |
Check notice
Code scanning / Robocop
Variable '{{ name }}' is assigned but not used Note test
| [Teardown] Run Keywords Get Kserve Events And Logs model_name=${TENSORFLOW_MODEL_NAME} | ||
| ... project_title=${PRJ_TITLE} | ||
| ... AND | ||
| ... Clean All Models Of Current User |
Check warning
Code scanning / Robocop
Line is too long ({{ line_length }}/{{ allowed_length }}) Warning test
| ... Clean All Models Of Current User | ||
| ... AND | ||
| ... Delete Serving Runtime Template From CLI displayed_name=triton-kserve-rest | ||
|
|
Check warning
Code scanning / Robocop
Line is too long ({{ line_length }}/{{ allowed_length }}) Warning test
Robot Results
|
|
| ... endpoint=inference.GRPCInferenceService/ModelInfer | ||
| ... json_body=@ input_filepath=${INFERENCE_GRPC_INPUT_KERAS} | ||
| ... insecure=${True} protobuf_file=${PROTOBUFF_FILE} json_header="Authorization: Bearer ${token}" | ||
| Log ${inference_output} |
Check notice
Code scanning / Robocop
Variable '{{ name }}' is assigned but not used Note test
| ... endpoint=inference.GRPCInferenceService/ModelInfer | ||
| ... json_body=@ input_filepath=${INFERENCE_GRPC_INPUT_KERAS} | ||
| ... insecure=${True} protobuf_file=${PROTOBUFF_FILE} json_header="Authorization: Bearer ${token}" | ||
| Log ${inference_output} |
Check notice
Code scanning / Robocop
Variable '{{ name }}' is assigned but not used Note test
bdattoma
merged commit aab4916
into
red-hat-data-services:releases/2.16.0
No description provided.