[Usage]: how to use vllm to output code only

[shaoyuyoung]

Your current environment

None

How would you like to use vllm

Hi, guys!
How can I use vLLM to output the code only, preventing additional explanations from the model.

It seems that the deepseek API supports this function (refer to https://api-docs.deepseek.com/guides/chat_prefix_completion)

I didn't find any instructions about this in the doc of vLLM. Does vLLM support this? (I know one possible way is to extract the code using re, match the pattern ```python\s([\s\S]*?)``` )
Thx if anybody can help me.

Before submitting a new issue...

• Make sure you already searched for relevant issues, and asked the chatbot living at the bottom right corner of the documentation page, which can answer lots of frequently asked questions.