jandres/GenAIExamples
1
0
Fork 0
Code Issues Pull Requests Actions 4 Packages Projects Releases Wiki Activity

Adding files to deploy CodeGen application on ROCm vLLM (#1544)

Browse Source 
Signed-off-by: Chingis Yundunov <YundunovCN@sibedge.com>
This commit is contained in:
chyundunovDatamonsters
2025-03-24 13:45:17 +07:00
committed by GitHub
parent fe2a6674e0
commit 31b1d69e40
10 changed files with 689 additions and 67 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
CodeGen/tests/test_compose_on_rocm.sh
View File

@@ -34,7 +34,7 @@ function build_docker_images() {
service_list="codegen codegen-ui llm-textgen"
docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log
docker pull ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu
docker pull ghcr.io/huggingface/text-generation-inference:2.3.1-rocm
docker images && sleep 1s
}
@@ -51,7 +51,7 @@ function start_services() {
export CODEGEN_BACKEND_SERVICE_PORT=7778
export CODEGEN_BACKEND_SERVICE_URL="http://${ip_address}:${CODEGEN_BACKEND_SERVICE_PORT}/v1/codegen"
export CODEGEN_UI_SERVICE_PORT=5173
export host_ip=${ip_address}
export HOST_IP=${ip_address}
sed -i "s/backend_address/$ip_address/g" $WORKPATH/ui/svelte/.env
@@ -100,15 +100,15 @@ function validate_services() {
function validate_microservices() {
# tgi for llm service
validate_services \
"${ip_address}:8028/generate" \
"${ip_address}:${CODEGEN_TGI_SERVICE_PORT}/generate" \
"generated_text" \
"codegen-tgi-service" \
"codegen-tgi-service" \
'{"inputs":"def print_hello_world():","parameters":{"max_new_tokens":256, "do_sample": true}}'
sleep 10
# llm microservice
validate_services \
"${ip_address}:9000/v1/chat/completions" \
"${ip_address}:${CODEGEN_LLM_SERVICE_PORT}/v1/chat/completions" \
"data: " \
"codegen-llm-server" \
"codegen-llm-server" \

181
CodeGen/tests/test_compose_vllm_on_rocm.sh Normal file
View File

@@ -0,0 +1,181 @@
#!/bin/bash
# Copyright (C) 2024 Intel Corporation
# Copyright (c) 2024 Advanced Micro Devices, Inc.
# SPDX-License-Identifier: Apache-2.0
set -xe
IMAGE_REPO=${IMAGE_REPO:-"opea"}
IMAGE_TAG=${IMAGE_TAG:-"latest"}
echo "REGISTRY=IMAGE_REPO=${IMAGE_REPO}"
echo "TAG=IMAGE_TAG=${IMAGE_TAG}"
export REGISTRY=${IMAGE_REPO}
export TAG=${IMAGE_TAG}
WORKPATH=$(dirname "$PWD")
LOG_PATH="$WORKPATH/tests"
ip_address=$(hostname -I | awk '{print $1}')
function build_docker_images() {
opea_branch=${opea_branch:-"main"}
# If the opea_branch isn't main, replace the git clone branch in Dockerfile.
if [[ "${opea_branch}" != "main" ]]; then
cd $WORKPATH
OLD_STRING="RUN git clone --depth 1 https://github.com/opea-project/GenAIComps.git"
NEW_STRING="RUN git clone --depth 1 --branch ${opea_branch} https://github.com/opea-project/GenAIComps.git"
find . -type f -name "Dockerfile*" | while read -r file; do
echo "Processing file: $file"
sed -i "s|$OLD_STRING|$NEW_STRING|g" "$file"
done
fi
cd $WORKPATH/docker_image_build
git clone --depth 1 --branch ${opea_branch} https://github.com/opea-project/GenAIComps.git
echo "Build all the images with --no-cache, check docker_image_build.log for details..."
service_list="vllm-rocm llm-textgen codegen codegen-ui"
docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log
docker images && sleep 1s
}
function start_services() {
cd $WORKPATH/docker_compose/amd/gpu/rocm/
export CODEGEN_LLM_MODEL_ID="Qwen/Qwen2.5-Coder-7B-Instruct"
export CODEGEN_VLLM_SERVICE_PORT=8028
export CODEGEN_VLLM_ENDPOINT="http://${ip_address}:${CODEGEN_VLLM_SERVICE_PORT}"
export CODEGEN_LLM_SERVICE_PORT=9000
export CODEGEN_HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
export CODEGEN_MEGA_SERVICE_HOST_IP=${ip_address}
export CODEGEN_LLM_SERVICE_HOST_IP=${ip_address}
export CODEGEN_BACKEND_SERVICE_PORT=7778
export CODEGEN_BACKEND_SERVICE_URL="http://${ip_address}:${CODEGEN_BACKEND_SERVICE_PORT}/v1/codegen"
export CODEGEN_UI_SERVICE_PORT=5173
export HOST_IP=${ip_address}
sed -i "s/backend_address/$ip_address/g" $WORKPATH/ui/svelte/.env
# Start Docker Containers
docker compose -f compose_vllm.yaml up -d > ${LOG_PATH}/start_services_with_compose.log
n=0
until [[ "$n" -ge 500 ]]; do
docker logs codegen-vllm-service >& "${LOG_PATH}"/codegen-vllm-service_start.log
if grep -q "Application startup complete" "${LOG_PATH}"/codegen-vllm-service_start.log; then
break
fi
sleep 20s
n=$((n+1))
done
}
function validate_services() {
local URL="$1"
local EXPECTED_RESULT="$2"
local SERVICE_NAME="$3"
local DOCKER_NAME="$4"
local INPUT_DATA="$5"
local HTTP_STATUS=$(curl -s -o /dev/null -w "%{http_code}" -X POST -d "$INPUT_DATA" -H 'Content-Type: application/json' "$URL")
if [ "$HTTP_STATUS" -eq 200 ]; then
echo "[ $SERVICE_NAME ] HTTP status is 200. Checking content..."
local CONTENT=$(curl -s -X POST -d "$INPUT_DATA" -H 'Content-Type: application/json' "$URL" | tee ${LOG_PATH}/${SERVICE_NAME}.log)
if echo "$CONTENT" | grep -q "$EXPECTED_RESULT"; then
echo "[ $SERVICE_NAME ] Content is as expected."
else
echo "[ $SERVICE_NAME ] Content does not match the expected result: $CONTENT"
docker logs ${DOCKER_NAME} >> ${LOG_PATH}/${SERVICE_NAME}.log
exit 1
fi
else
echo "[ $SERVICE_NAME ] HTTP status is not 200. Received status was $HTTP_STATUS"
docker logs ${DOCKER_NAME} >> ${LOG_PATH}/${SERVICE_NAME}.log
exit 1
fi
sleep 5s
}
function validate_microservices() {
# vLLM for llm service
validate_services \
"${ip_address}:${CODEGEN_VLLM_SERVICE_PORT}/v1/chat/completions" \
"content" \
"codegen-vllm-service" \
"codegen-vllm-service" \
'{"model": "Qwen/Qwen2.5-Coder-7B-Instruct", "messages": [{"role": "user", "content": "What is Deep Learning?"}], "max_tokens": 17}'
sleep 10
# llm microservice
validate_services \
"${ip_address}:${CODEGEN_LLM_SERVICE_PORT}/v1/chat/completions" \
"data: " \
"codegen-llm-server" \
"codegen-llm-server" \
'{"query":"def print_hello_world():"}'
}
function validate_megaservice() {
# Curl the Mega Service
validate_services \
"${ip_address}:${CODEGEN_BACKEND_SERVICE_PORT}/v1/codegen" \
"print" \
"codegen-backend-server" \
"codegen-backend-server" \
'{"messages": "def print_hello_world():"}'
}
function validate_frontend() {
cd $WORKPATH/ui/svelte
local conda_env_name="OPEA_e2e"
export PATH=${HOME}/miniconda3/bin/:$PATH
if conda info --envs | grep -q "$conda_env_name"; then
echo "$conda_env_name exist!"
else
conda create -n ${conda_env_name} python=3.12 -y
fi
source activate ${conda_env_name}
sed -i "s/localhost/$ip_address/g" playwright.config.ts
conda install -c conda-forge nodejs=22.6.0 -y
npm install && npm ci && npx playwright install --with-deps
node -v && npm -v && pip list
exit_status=0
npx playwright test || exit_status=$?
if [ $exit_status -ne 0 ]; then
echo "[TEST INFO]: ---------frontend test failed---------"
exit $exit_status
else
echo "[TEST INFO]: ---------frontend test passed---------"
fi
}
function stop_docker() {
echo "OPENAI_API_KEY - ${OPENAI_API_KEY}"
cd $WORKPATH/docker_compose/amd/gpu/rocm/
docker compose -f compose_vllm.yaml stop && docker compose -f compose_vllm.yaml rm -f
}
function main() {
stop_docker
if [[ "$IMAGE_REPO" == "opea" ]]; then build_docker_images; fi
start_services
validate_microservices
validate_megaservice
validate_frontend
stop_docker
echo y | docker system prune
cd $WORKPATH
}
main