### What this PR does / why we need it? To solve the problem of the issue:https://github.com/vllm-project/vllm-ascend/issues/2262 - support for cross-attention when the model is encoder-decoder - support for whisper model - vLLM version: v0.13.0 - vLLM main: https://github.com/vllm-project/vllm/commit/7157596103666ee7ccb7008acee8bff8a8ff1731 Signed-off-by: gh924 <guihao2@huawei.com> Co-authored-by: Aoxuan Chen <43376869+chenaoxuan@users.noreply.github.com>