From b749da8a2b70bcba37f6e575ad46cdcc913575af Mon Sep 17 00:00:00 2001
From: ZePan110 <ze.pan@intel.com>
Date: Wed, 14 Aug 2024 14:47:26 +0800
Subject: [PATCH] Fix issue (#483)

* Standardize image names and labels.

Signed-off-by: zepan <ze.pan@intel.com>

* Remove test cases that are no longer in use.

Signed-off-by: zepan <ze.pan@intel.com>

---------

Signed-off-by: zepan <ze.pan@intel.com>
Signed-off-by: BaoHuiling <huiling.bao@intel.com>
---
 tests/test_llms_text-generation_ray_serve.sh | 98 --------------------
 tests/test_llms_text-generation_vllm-ray.sh  |  2 +-
 2 files changed, 1 insertion(+), 99 deletions(-)
 delete mode 100644 tests/test_llms_text-generation_ray_serve.sh

diff --git a/tests/test_llms_text-generation_ray_serve.sh b/tests/test_llms_text-generation_ray_serve.sh
deleted file mode 100644
index 5ceabef6d..000000000
--- a/tests/test_llms_text-generation_ray_serve.sh
+++ /dev/null
@@ -1,98 +0,0 @@
-#!/bin/bash
-# Copyright (C) 2024 Intel Corporation
-# SPDX-License-Identifier: Apache-2.0
-
-set -xe
-
-WORKPATH=$(dirname "$PWD")
-ip_address=$(hostname -I | awk '{print $1}')
-
-function build_docker_images() {
-    ## Build VLLM Ray docker
-    cd $WORKPATH
-    docker build \
-        -f comps/llms/text-generation/ray_serve/docker/Dockerfile.rayserve \
-        --network=host \
-        -t ray_serve_habana:comps .
-
-    ## Build OPEA microservice docker
-    cd $WORKPATH
-    docker build  \
-        -t opea/llm-ray:comps \
-        -f comps/llms/text-generation/ray_serve/docker/Dockerfile.microservice .
-}
-
-function start_service() {
-    export LLM_MODEL="facebook/opt-125m"
-    port_number=8008
-
-    docker run -d --rm \
-        --runtime=habana \
-        --name="test-comps-ray-service" \
-        -v $PWD/data:/data \
-        -e HABANA_VISIBLE_DEVICES=all \
-        -e OMPI_MCA_btl_vader_single_copy_mechanism=none \
-        --cap-add=sys_nice \
-        --ipc=host \
-        -p $port_number:80 \
-        -e HF_TOKEN=${HUGGINGFACEHUB_API_TOKEN} \
-        -e TRUST_REMOTE_CODE=True \
-        ray_serve:habana \
-        /bin/bash -c "ray start --head && python api_server_openai.py --port_number 80 --model_id_or_path $LLM_MODEL --chat_processor ChatModelLlama --num_cpus_per_worker 8 --num_hpus_per_worker 1"
-
-    export RAY_Serve_ENDPOINT="http://${ip_address}:${port_number}"
-    docker run -d --rm \
-        --name="test-comps-ray-microserve" \
-        -p 9000:9000 \
-        --ipc=host \
-        -e RAY_Serve_ENDPOINT=$RAY_Serve_ENDPOINT \
-        -e HUGGINGFACEHUB_API_TOKEN=$HUGGINGFACEHUB_API_TOKEN \
-        -e LLM_MODEL=$LLM_MODEL \
-        opea/llm-ray:comps
-
-    # check whether ray is fully ready
-    n=0
-    until [[ "$n" -ge 100 ]] || [[ $ready == true ]]; do
-        docker logs test-comps-ray-service > ${WORKPATH}/tests/test-comps-ray-service.log
-        n=$((n+1))
-        if grep -q Connected ${WORKPATH}/tests/test-comps-ray-service.log; then
-            break
-        fi
-        sleep 5s
-    done
-    sleep 5s
-}
-
-function validate_microservice() {
-    http_proxy="" curl http://${ip_address}:8008/v1/chat/completions   \
-        -H "Content-Type: application/json"   \
-        -d '{"model": "opt-125m", "messages": [{"role": "user", "content": "What is Deep Learning?"}], "max_tokens": 32 }'
-    http_proxy="" curl http://${ip_address}:9000/v1/chat/completions \
-        -X POST \
-        -d '{"query":"What is Deep Learning?","max_new_tokens":17,"top_k":10,"top_p":0.95,"typical_p":0.95,"temperature":0.01,"repetition_penalty":1.03,"streaming":false}' \
-        -H 'Content-Type: application/json'
-    docker logs test-comps-ray-service
-    docker logs test-comps-ray-microserve
-        }
-
-
-function stop_docker() {
-    cid=$(docker ps -aq --filter "name=test-comps-ray*")
-    if [[ ! -z "$cid" ]]; then docker rm $cid -f && sleep 1s; fi
-}
-
-function main() {
-
-    stop_docker
-
-    build_docker_images
-    start_service
-
-    validate_microservice
-
-    stop_docker
-    # echo y | docker system prune
-
-}
-
-main
diff --git a/tests/test_llms_text-generation_vllm-ray.sh b/tests/test_llms_text-generation_vllm-ray.sh
index 6364690e8..52a920b33 100644
--- a/tests/test_llms_text-generation_vllm-ray.sh
+++ b/tests/test_llms_text-generation_vllm-ray.sh
@@ -34,7 +34,7 @@ function start_service() {
         --ipc=host \
         -e HUGGINGFACEHUB_API_TOKEN=$HUGGINGFACEHUB_API_TOKEN \
         -p $port_number:8000 \
-        opea/vllm_ray:habana \
+        opea/vllm_ray-habana:comps \
         /bin/bash -c "ray start --head && python vllm_ray_openai.py --port_number 8000 --model_id_or_path $LLM_MODEL --tensor_parallel_size 2 --enforce_eager False"
 
     export vLLM_RAY_ENDPOINT="http://${ip_address}:${port_number}"