Fix Dockerfile error and add CI test for IPEX

[lvliang-intel]

Description

Fix Dockerfile error and add CI test for IPEX

Issues

n/a

Type of change

List the type of change like below. Please delete options that are not relevant.

• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds new functionality)
• Breaking change (fix or feature that would break existing design and interface)
• Others (enhancement, documentation, validation, etc.)

Dependencies

None.

Tests

Local test and CI test.

++ dirname /home/lvl/GenAIComps/tests

• WORKPATH=/home/lvl/GenAIComps
  ++ hostname -I
  ++ awk '{print $1}'
• ip_address=10.7.4.57
• export DATA_PATH=
• DATA_PATH=
• main
• validate_microservice
• echo 'Validate microservice started'
  Validate microservice started
  ++ http_proxy=
  ++ curl http://localhost:8688/v1/chat/completions -X POST -H 'Content-Type: application/json' -d '{
  "model": "microsoft/Phi-4-mini-instruct",
  "messages": [
  {"role": "user", "content": "What is Deep Learning?"}
  ],
  "max_tokens": 128
  }'
  % Total % Received % Xferd Average Speed Time Time Time Current
  Dload Upload Total Spent Left Speed
  100 879 100 721 100 158 17 3 0:00:52 0:00:40 0:00:12 158
• result='["What is Deep Learning?** \n\nDeep learning is a subset of machine learning in artificial intelligence that has networks capable of learning unsupervised from data that is unstructured or unlabeled. Deep learning is also known as deep neural learning or deep neural network.\n\nTo put it simply, it is a neural network with three or more layers. These neural networks attempt to simulate the behavior of the human brain—albeit far from matching its ability—in order to "learn" from large amounts of data. While a neural network with a single layer can still make approximate predictions, additional hidden layers can help optimize the accuracy.\n\nWhy is Deep Learning Important?\n\nDeep learning frameworks"]'
• [[ ["What is Deep Learning?** \n\nDeep learning is a subset of machine learning in artificial intelligence that has networks capable of learning unsupervised from data that is unstructured or unlabeled. Deep learning is also known as deep neural learning or deep neural network.\n\nTo put it simply, it is a neural network with three or more layers. These neural networks attempt to simulate the behavior of the human brain—albeit far from matching its ability—in order to "learn" from large amounts of data. While a neural network with a single layer can still make approximate predictions, additional hidden layers can help optimize the accuracy.\n\nWhy is Deep Learning Important?\n\nDeep learning frameworks"] == \D\e\e\p ]]
• echo 'Result correct.'
  Result correct.
• stop_docker
  ++ docker ps -aq --filter name=ipex-llm-server
• cid=ac50824e2d82
• echo 'Shutdown legacy containers ac50824e2d82'
  Shutdown legacy containers ac50824e2d82
• [[ ! -z ac50824e2d82 ]]
• docker stop ac50824e2d82
  ac50824e2d82
• docker rm ac50824e2d82
  ac50824e2d82
• sleep 1s
• echo 'cleanup container images and volumes'
  cleanup container images and volumes
• echo y
• docker system prune