### What this PR does / why we need it? qwen2.5-vl-72b reports a shape ERROR during the _prepare_inputs phase under high concurrency【 issue https://github.com/vllm-project/vllm-ascend/issues/4430 】 This PR fix it. The related PR in main branch :https://github.com/vllm-project/vllm-ascend/pull/3612 The related commit in vllm : https://github.com/vllm-project/vllm/blob/17c540a993af88204ad1b78345c8a865cf58ce44/vllm/model_executor/models/interfaces.py 【The _get_text_embeddings function has been refactored to interfaces.pyin vllm.】 Signed-off-by: Levi-JQ <yujinqi2@huawei.com> Co-authored-by: Levi-JQ <yujinqi2@huawei.com>