### What this PR does / why we need it? perf: use multicast to avoid padding decode request to prefill size ### How was this patch tested? - vLLM version: v0.9.1 - vLLM main: https://github.com/vllm-project/vllm/commit/1fd471e957526a34a0cb4b60d2e830cd6ca79fdc Signed-off-by: boying <897013703@qq.com>