[vLLM] QBits Perf Enhence

[Zhenzhong1]

Type of Change

• Added customized config & updated benchmark script
• Fixed the vLLM-qbits 1024 in,32 out next token issues

Description

vLLM perf:

Expected Behavior & Potential Risk

N/A

How has this PR been tested?

Manually profiling.

Dependency Change?

N/A

[github-actions]

⚡ Required checks status: All passing 🟢

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/transformers/llm/quantization/nn/modules.py, intel_extension_for_transformers/transformers/modeling/modeling_auto.py.

🟢 Optimize Unit Test workflow

Check ID	Status	Error details
optimize-unit-test-baseline	success		✅
optimize-unit-test-PR-test	success		✅
Genreate-OptimizeUT-Report	success		✅

These checks are required after the changes to intel_extension_for_transformers/transformers/llm/quantization/nn/modules.py, intel_extension_for_transformers/transformers/modeling/modeling_auto.py.

🟢 NeuralChat Unit Test

Check ID	Status	Error details
neuralchat-unit-test-baseline	success		✅
neuralchat-unit-test-PR-test	success		✅
Generate-NeuralChat-Report	success		✅

These checks are required after the changes to intel_extension_for_transformers/transformers/llm/quantization/nn/modules.py, intel_extension_for_transformers/transformers/modeling/modeling_auto.py.

🟢 Engine Unit Test workflow

Check ID	Status	Error details
engine-unit-test-baseline	success		✅
engine-unit-test-PR-test	success		✅
Genreate-Engine-Report	success		✅

These checks are required after the changes to intel_extension_for_transformers/transformers/llm/quantization/nn/modules.py, intel_extension_for_transformers/transformers/modeling/modeling_auto.py.

🟢 Chat Bot Test workflow

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

These checks are required after the changes to intel_extension_for_transformers/transformers/llm/quantization/nn/modules.py, intel_extension_for_transformers/transformers/modeling/modeling_auto.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.

[Zhenzhong1]

@XuehaoSun Hi, if this Optimize Unit Test CI issue fixed, please let me know and re-run the CI. Thx.

[Zhenzhong1]

ready for merge.