Skip to content

Commit

Permalink
add container checks to llm models suite
Browse files Browse the repository at this point in the history
  • Loading branch information
@bdattoma
bdattoma committed Apr 24, 2024
1 parent dce4ce1 commit be5e6a1
Showing 1 changed file with 18 additions and 18 deletions.
36 changes: 18 additions & 18 deletions ...ests/Tests/400__ods_dashboard/420__model_serving/LLMs/422__model_serving_llm_models.robot
View file
Original file line number Diff line number Diff line change
Expand Up @@ -36,8 +36,8 @@ Verify User Can Serve And Query A bigscience/mt0-xxl Model
... limits_dict=${limits} requests_dict=${requests} kserve_mode=${KSERVE_MODE}
Deploy Model Via CLI isvc_filepath=${INFERENCESERVICE_FILLED_FILEPATH}
... namespace=${test_namespace}
Wait For Pods To Be Ready label_selector=serving.kserve.io/inferenceservice=${model_name}
... namespace=${test_namespace} timeout=900s
Wait For Model KServe Deployment To Be Ready label_selector=serving.kserve.io/inferenceservice=${model_name}
... namespace=${test_namespace} runtime=${TGIS_RUNTIME_NAME} timeout=900s
${pod_name}= Get Pod Name namespace=${test_namespace} label_selector=serving.kserve.io/inferenceservice=${model_name}
Run Keyword If "${KSERVE_MODE}"=="RawDeployment"
... Start Port-forwarding namespace=${test_namespace} pod_name=${pod_name}
Expand Down Expand Up @@ -82,8 +82,8 @@ Verify User Can Serve And Query A google/flan-t5-xl Model
... limits_dict=${limits} requests_dict=${requests} kserve_mode=${KSERVE_MODE}
Deploy Model Via CLI isvc_filepath=${INFERENCESERVICE_FILLED_FILEPATH}
... namespace=${test_namespace}
Wait For Pods To Be Ready label_selector=serving.kserve.io/inferenceservice=${model_name}
... namespace=${test_namespace} timeout=900s
Wait For Model KServe Deployment To Be Ready label_selector=serving.kserve.io/inferenceservice=${model_name}
... namespace=${test_namespace} runtime= ${TGIS_RUNTIME_NAME} timeout=900s
${pod_name}= Get Pod Name namespace=${test_namespace} label_selector=serving.kserve.io/inferenceservice=${model_name}
Run Keyword If "${KSERVE_MODE}"=="RawDeployment"
... Start Port-forwarding namespace=${test_namespace} pod_name=${pod_name}
Expand Down Expand Up @@ -128,8 +128,8 @@ Verify User Can Serve And Query A google/flan-t5-xxl Model
... limits_dict=${limits} requests_dict=${requests} kserve_mode=${KSERVE_MODE}
Deploy Model Via CLI isvc_filepath=${INFERENCESERVICE_FILLED_FILEPATH}
... namespace=${test_namespace}
Wait For Pods To Be Ready label_selector=serving.kserve.io/inferenceservice=${model_name}
... namespace=${test_namespace} timeout=900s
Wait For Model KServe Deployment To Be Ready label_selector=serving.kserve.io/inferenceservice=${model_name}
... namespace=${test_namespace} runtime= ${TGIS_RUNTIME_NAME} timeout=900s
${pod_name}= Get Pod Name namespace=${test_namespace} label_selector=serving.kserve.io/inferenceservice=${model_name}
Run Keyword If "${KSERVE_MODE}"=="RawDeployment"
... Start Port-forwarding namespace=${test_namespace} pod_name=${pod_name}
Expand Down Expand Up @@ -173,8 +173,8 @@ Verify User Can Serve And Query A elyza/elyza-japanese-llama-2-7b-instruct Model
... limits_dict=${limits} requests_dict=${requests} kserve_mode=${KSERVE_MODE}
Deploy Model Via CLI isvc_filepath=${INFERENCESERVICE_FILLED_FILEPATH}
... namespace=${test_namespace}
Wait For Pods To Be Ready label_selector=serving.kserve.io/inferenceservice=${model_name}
... namespace=${test_namespace} timeout=900s
Wait For Model KServe Deployment To Be Ready label_selector=serving.kserve.io/inferenceservice=${model_name}
... namespace=${test_namespace} runtime= ${TGIS_RUNTIME_NAME} timeout=900s
${pod_name}= Get Pod Name namespace=${test_namespace} label_selector=serving.kserve.io/inferenceservice=${model_name}
Run Keyword If "${KSERVE_MODE}"=="RawDeployment"
... Start Port-forwarding namespace=${test_namespace} pod_name=${pod_name}
Expand Down Expand Up @@ -219,8 +219,8 @@ Verify User Can Serve And Query A ibm/mpt-7b-instruct2 Model
... limits_dict=${limits} requests_dict=${requests} kserve_mode=${KSERVE_MODE}
Deploy Model Via CLI isvc_filepath=${INFERENCESERVICE_FILLED_FILEPATH}
... namespace=${test_namespace}
Wait For Pods To Be Ready label_selector=serving.kserve.io/inferenceservice=${model_name}
... namespace=${test_namespace} timeout=900s
Wait For Model KServe Deployment To Be Ready label_selector=serving.kserve.io/inferenceservice=${model_name}
... namespace=${test_namespace} runtime= ${TGIS_RUNTIME_NAME} timeout=900s
${pod_name}= Get Pod Name namespace=${test_namespace} label_selector=serving.kserve.io/inferenceservice=${model_name}
Run Keyword If "${KSERVE_MODE}"=="RawDeployment"
... Start Port-forwarding namespace=${test_namespace} pod_name=${pod_name}
Expand Down Expand Up @@ -265,8 +265,8 @@ Verify User Can Serve And Query A google/flan-ul-2 Model
... limits_dict=${limits} requests_dict=${requests} kserve_mode=${KSERVE_MODE}
Deploy Model Via CLI isvc_filepath=${INFERENCESERVICE_FILLED_FILEPATH}
... namespace=${test_namespace}
Wait For Pods To Be Ready label_selector=serving.kserve.io/inferenceservice=${model_name}
... namespace=${test_namespace} timeout=900s
Wait For Model KServe Deployment To Be Ready label_selector=serving.kserve.io/inferenceservice=${model_name}
... namespace=${test_namespace} runtime= ${TGIS_RUNTIME_NAME} timeout=900s
${pod_name}= Get Pod Name namespace=${test_namespace} label_selector=serving.kserve.io/inferenceservice=${model_name}
Run Keyword If "${KSERVE_MODE}"=="RawDeployment"
... Start Port-forwarding namespace=${test_namespace} pod_name=${pod_name}
Expand Down Expand Up @@ -311,8 +311,8 @@ Verify User Can Serve And Query A codellama/codellama-34b-instruct-hf Model
... limits_dict=${limits} requests_dict=${requests} kserve_mode=${KSERVE_MODE}
Deploy Model Via CLI isvc_filepath=${INFERENCESERVICE_FILLED_FILEPATH}
... namespace=${test_namespace}
Wait For Pods To Be Ready label_selector=serving.kserve.io/inferenceservice=${model_name}
... namespace=${test_namespace} timeout=3000s
Wait For Model KServe Deployment To Be Ready label_selector=serving.kserve.io/inferenceservice=${model_name}
... namespace=${test_namespace} runtime= ${TGIS_RUNTIME_NAME} timeout=3000s
${pod_name}= Get Pod Name namespace=${test_namespace} label_selector=serving.kserve.io/inferenceservice=${model_name}
Run Keyword If "${KSERVE_MODE}"=="RawDeployment"
... Start Port-forwarding namespace=${test_namespace} pod_name=${pod_name}
Expand Down Expand Up @@ -348,8 +348,8 @@ Verify User Can Serve And Query A meta-llama/llama-2-13b-chat Model
... limits_dict=${limits} requests_dict=${requests} kserve_mode=${KSERVE_MODE}
Deploy Model Via CLI isvc_filepath=${INFERENCESERVICE_FILLED_FILEPATH}
... namespace=${test_namespace}
Wait For Pods To Be Ready label_selector=serving.kserve.io/inferenceservice=${model_name}
... namespace=${test_namespace} timeout=900s
Wait For Model KServe Deployment To Be Ready label_selector=serving.kserve.io/inferenceservice=${model_name}
... namespace=${test_namespace} runtime= ${TGIS_RUNTIME_NAME} timeout=900s
${pod_name}= Get Pod Name namespace=${test_namespace} label_selector=serving.kserve.io/inferenceservice=${model_name}
Run Keyword If "${KSERVE_MODE}"=="RawDeployment"
... Start Port-forwarding namespace=${test_namespace} pod_name=${pod_name}
Expand Down Expand Up @@ -399,8 +399,8 @@ Verify User Can Serve And Query A google/flan-t5-xl Prompt Tuned Model
... overlays=${overlays}
Deploy Model Via CLI isvc_filepath=${INFERENCESERVICE_FILLED_FILEPATH}
... namespace=${test_namespace}
Wait For Pods To Be Ready label_selector=serving.kserve.io/inferenceservice=${model_name}
... namespace=${test_namespace} timeout=300s
Wait For Model KServe Deployment To Be Ready label_selector=serving.kserve.io/inferenceservice=${model_name}
... namespace=${test_namespace} runtime= ${TGIS_RUNTIME_NAME} timeout=300s
${pod_name}= Get Pod Name namespace=${test_namespace} label_selector=serving.kserve.io/inferenceservice=${model_name}
Run Keyword If "${KSERVE_MODE}"=="RawDeployment"
... Start Port-forwarding namespace=${test_namespace} pod_name=${pod_name}
Expand Down

0 comments on commit be5e6a1

Please sign in to comment.