From 6c0c3d9c999c36995281a8f0d6c61c350c047411 Mon Sep 17 00:00:00 2001 From: Luca Giorgi Date: Thu, 16 May 2024 14:12:45 +0200 Subject: [PATCH] small cleanup Signed-off-by: Luca Giorgi --- ods_ci/tests/Resources/Files/llm/vllm/query.json | 13 ------------- .../LLMs/vllm/426__model_serving_vllm_metrics.robot | 7 ++----- 2 files changed, 2 insertions(+), 18 deletions(-) delete mode 100644 ods_ci/tests/Resources/Files/llm/vllm/query.json diff --git a/ods_ci/tests/Resources/Files/llm/vllm/query.json b/ods_ci/tests/Resources/Files/llm/vllm/query.json deleted file mode 100644 index 156795eda..000000000 --- a/ods_ci/tests/Resources/Files/llm/vllm/query.json +++ /dev/null @@ -1,13 +0,0 @@ -{ - "model": "gpt2", - "messages": [ - { - "role": "system", - "content": "You are a poetic assistant, skilled in explaining complex programming concepts with creative flair." - }, - { - "role": "user", - "content": "Compose a poem that explains the concept of recursion in programming." - } - ] -} \ No newline at end of file diff --git a/ods_ci/tests/Tests/400__ods_dashboard/420__model_serving/LLMs/vllm/426__model_serving_vllm_metrics.robot b/ods_ci/tests/Tests/400__ods_dashboard/420__model_serving/LLMs/vllm/426__model_serving_vllm_metrics.robot index 35b0cc421..755bccc55 100644 --- a/ods_ci/tests/Tests/400__ods_dashboard/420__model_serving/LLMs/vllm/426__model_serving_vllm_metrics.robot +++ b/ods_ci/tests/Tests/400__ods_dashboard/420__model_serving/LLMs/vllm/426__model_serving_vllm_metrics.robot @@ -19,9 +19,6 @@ ${VLLM_RESOURCES_DIRPATH}= ods_ci/tests/Resources/Files/llm/vllm ${DL_POD_FILEPATH}= ${VLLM_RESOURCES_DIRPATH}/download_model.yaml ${SR_FILEPATH}= ${VLLM_RESOURCES_DIRPATH}/vllm_servingruntime.yaml ${IS_FILEPATH}= ${VLLM_RESOURCES_DIRPATH}/vllm-gpt2_inferenceservice.yaml -${INFERENCE_INPUT}= @${VLLM_RESOURCES_DIRPATH}/query.json -${INFERENCE_URL}= http://localhost:8080/v1/chat/completions -${METRICS_URL}= http://localhost:8080/metrics/ ${TEST_NS}= vllm-gpt2 @{SEARCH_METRICS}= vllm:cache_config_info ... vllm:num_requests_running @@ -47,7 +44,7 @@ ${TEST_NS}= vllm-gpt2 *** Test Cases *** Verify User Can Deploy A Model With Vllm Via CLI [Documentation] Deploy a model (gpt2) using the vllm runtime and confirm that it's running - [Tags] Tier1 Sanity Resources-GPU ODS-XXX + [Tags] Tier1 Sanity Resources-GPU RHOAIENG-6264 ${rc} ${out}= Run And Return Rc And Output oc apply -f ${DL_POD_FILEPATH} Should Be Equal As Integers ${rc} ${0} Wait For Pods To Succeed label_selector=gpt-download-pod=true namespace=${TEST_NS} @@ -62,7 +59,7 @@ Verify User Can Deploy A Model With Vllm Via CLI Verify Vllm Metrics Are Present [Documentation] Confirm vLLM metrics are exposed in OpenShift metrics - [Tags] Tier1 Sanity Resources-GPU ODS-XXX + [Tags] Tier1 Sanity Resources-GPU RHOAIENG-6264 ${host} = llm.Get KServe Inference Host Via CLI isvc_name=vllm-gpt2-openai namespace=${TEST_NS} ${rc} ${out}= Run And Return Rc And Output ... curl -ks ${host}/metrics/