update ipex api

[LJ-underdog]

Type of Change

feature or bug fix or documentation or others
API changed or not
yes

Description

update ipex api
detail description

[github-actions]

⛈️ Required checks status: Has failure 🔴

Warning
If you do not have the access to re-run the CI-Summary bot, please contact VincyZhang for help. If you push a new commit, all of the workflow will be re-triggered.

Groups summary

🟢 Format Scan Tests workflow

Check ID	Status	Error details
format-scan (pylint)	success		✅
format-scan (bandit)	success		✅
format-scan (cloc)	success		✅
format-scan (cpplint)	success		✅

These checks are required after the changes to intel_extension_for_transformers/neural_chat/models/model_utils.py.

🔴 NeuralChat Unit Test

Check ID	Status	Error details
neuralchat-unit-test-baseline	cancelled		🚫
neuralchat-unit-test-PR-test	failure	download	❌
Generate-NeuralChat-Report	skipped		❓

These checks are required after the changes to intel_extension_for_transformers/neural_chat/models/model_utils.py.

🟡 Chat Bot Test workflow

Check ID	Status	Error details
call-inference-llama-2-7b-chat-hf / inference test	no_status		❓
call-inference-mpt-7b-chat / inference test	no_status		❓

These checks are required after the changes to intel_extension_for_transformers/neural_chat/models/model_utils.py.

---

Thank you for your contribution! 💜

Note
This comment is automatically generated and will be updates every 180 seconds within the next 6 hours. If you have any other questions, contact VincyZhang or XuehaoSun for help.

[a32543254]

@changwangss could you help review this pr?

[changwangss]

Could you also change it (Line 849)? as I know, ipex.llm.optimize is recommanded to run bf16 LLMs inference by IPEX.

[a32543254]

LGTM

[a32543254]

convert to draft since the intel_ipex.llm.optimize will make the model cannot run.