[V1] [Feature] Collective RPC (#15444)

Signed-off-by: wwl2755 <wangwenlong2755@gmail.com>

vllm/v1/engine/llm_engine.py

@@ -2,7 +2,7 @@
 
 from collections.abc import Mapping
 from copy import copy
-from typing import Optional, Union
+from typing import Any, Callable, Optional, Union
 
 from typing_extensions import TypeVar
 
@@ -32,6 +32,7 @@ from vllm.v1.executor.abstract import Executor
 logger = init_logger(__name__)
 
 _G = TypeVar("_G", bound=BaseTokenizerGroup, default=BaseTokenizerGroup)
+_R = TypeVar("_R", default=Any)
 
 
 class LLMEngine:
@@ -282,6 +283,13 @@ class LLMEngine:
         """Prevent an adapter from being evicted."""
         return self.engine_core.pin_lora(lora_id)
 
+    def collective_rpc(self,
+                       method: Union[str, Callable[..., _R]],
+                       timeout: Optional[float] = None,
+                       args: tuple = (),
+                       kwargs: Optional[dict[str, Any]] = None) -> list[_R]:
+        return self.engine_core.collective_rpc(method, timeout, args, kwargs)
+
     def __del__(self):
         if dp_group := getattr(self, "dp_group", None):
             stateless_destroy_torch_distributed_process_group(dp_group)