[DOC] Add additional comments for LLMEngine and AsyncLLMEngine (#1011)

vllm/engine/async_llm_engine.py

@@ -253,7 +253,8 @@ class AsyncLLMEngine:
         log_requests: Whether to log the requests.
         start_engine_loop: If True, the background task to run the engine
             will be automatically started in the generate call.
-        *args, *kwargs: Arguments for LLMEngine.
+        *args: Arguments for LLMEngine.
+        *kwargs: Arguments for LLMEngine.
     """
 
     _engine_class: Type[_AsyncLLMEngine] = _AsyncLLMEngine
@@ -428,6 +429,49 @@ class AsyncLLMEngine:
         Yields:
             The output `RequestOutput` objects from the LLMEngine for the
             request.
+
+        Details:
+            - If the engine is not running, start the background loop,
+              which iteratively invokes
+              :meth:`~vllm.engine.async_llm_engine.AsyncLLMEngine.engine_step`
+              to process the waiting requests.
+            - Add the request to the engine's `RequestTracker`.
+              On the next background loop, this request will be sent to
+              the underlying engine.
+              Also, a corresponding `AsyncStream` will be created.
+            - Wait for the request outputs from `AsyncStream` and yield them.
+
+        Example:
+            >>> # Please refer to entrypoints/api_server.py for
+            >>> # the complete example.
+            >>>
+            >>> # initialize the engine and the example input
+            >>> engine = AsyncLLMEngine.from_engine_args(engine_args)
+            >>> example_input = {
+            >>>     "prompt": "What is LLM?",
+            >>>     "stream": False, # assume the non-streaming case
+            >>>     "temperature": 0.0,
+            >>>     "request_id": 0,
+            >>> }
+            >>>
+            >>> # start the generation
+            >>> results_generator = engine.generate(
+            >>>    example_input["prompt"],
+            >>>    SamplingParams(temperature=example_input["temperature"]),
+            >>>    example_input["request_id"])
+            >>>
+            >>> # get the results
+            >>> final_output = None
+            >>> async for request_output in results_generator:
+            >>>     if await request.is_disconnected():
+            >>>         # Abort the request if the client disconnects.
+            >>>         await engine.abort(request_id)
+            >>>         # Return or raise an error
+            >>>         ...
+            >>>     final_output = request_output
+            >>>
+            >>> # Process and return the final output
+            >>> ...
         """
         # Preprocess the request.
         # This should not be used for logging, as it is monotonic time.