[feat] Support prompt embedding caching for diffusion model (#2962)

Signed-off-by: knlnguyen1802 <knlnguyen1802@gmail.com>
Co-authored-by: Samit <285365963@qq.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>

vllm_omni/engine/async_omni_engine.py

@@ -1949,6 +1949,8 @@ class AsyncOmniEngine:
                 "mp" if kwargs.get("distributed_executor_backend") is None else kwargs["distributed_executor_backend"]
             ),
             "enable_sleep_mode": kwargs.get("enable_sleep_mode", False),
+            "enable_prompt_embed_cache": kwargs.get("enable_prompt_embed_cache", False),
+            "prompt_embed_cache_size": kwargs.get("prompt_embed_cache_size", 32),
             "enable_multithread_weight_load": kwargs.get("enable_multithread_weight_load", True),
             "num_weight_load_threads": kwargs.get("num_weight_load_threads", 4),
             "quantization": kwargs.get("quantization", None),