[Feature Request] support vLLM AsyncLLM for rollout

[ZongqiangZhang]

vLLM AsyncLLM mode is already available in verl, whose performance is better than vLLM sync mode.
Any plan to support AsyncLLM ?

related code:
https://github.com/volcengine/verl/blob/main/verl/workers/rollout/vllm_rollout/vllm_async_server.py#L181
verl-project/verl@aacd366