Add a cookbook on how to send batch requests with vLLM

[rlouf]

Some users may need to send batch requests with several prompt/schema pairs. It is possible to do this with the vLLM server integration using aiohttp, and we should document this.

[rbgo404]

Two ways of serving models using vLLM:

1. Online Mode: Which usage the OpenAI Client and expose the API's for text generation. Also you can create async request for token streaming. And IMO it does the dynamic batching for which you cannot explicitly mention the batch size.
2. Offline mode: This usage the llm.generate function where you can pass the batch of prompts.

For your usecase you can use vLLM on offline serving without using aiohttp