Enable vllm load gptq model

[hzjane]

Description

Enable vllm load gptq model.
Have tested Llama-2-13B-chat-GPTQ and Llama-2-7B-Chat-GPTQ will vllm.

1. Why the change?

2. User API changes

Only supports asym_int4.

llm = LLM(model="/llm/models/Llama-2-13B-chat-GPTQ",
          quantization="GPTQ",
          load_in_low_bit="asym_int4",
          ....
)

or

python -m ipex_llm.vllm.xpu.entrypoints.openai.api_server \
--quantization gptq
--load-in-low-bit asym_int4
...

3. Summary of the change

4. How to test?

• N/A
• Unit test: Please manually trigger the PR Validation here by inputting the PR number (e.g., 1234). And paste your action link here once it has been successfully finished.
• Application test
• Document test
• ...

5. New dependencies

• New Python dependencies
  - Dependency1
  - Dependency2
  - ...
• New Java/Scala dependencies and their license
  - Dependency1 and license1
  - Dependency2 and license2
  - ...

[jason-dai]

convert_vllm_awq_or_gptq

[glorysdj]

LGTM