fixes for removing prints and mock server

Author: markurtz

src/guidellm/__main__.py

@@ -43,7 +43,7 @@
 from guidellm.benchmark.scenario import (
     GenerativeTextScenario,
 )
-from guidellm.mock_server import MockServer, ServerConfig
+from guidellm.mock_server import MockServer, MockServerConfig
 from guidellm.preprocess.dataset import ShortPromptStrategy, process_dataset
 from guidellm.scheduler import StrategyType
 from guidellm.settings import print_config
@@ -658,6 +658,7 @@ def dataset(
 @click.option(
     "--model", default="llama-3.1-8b-instruct", help="The name of the model to mock"
 )
+@click.option("--processor", default=None, help="The processor to use for requests")
 @click.option(
     "--request-latency",
     default=3,
@@ -721,6 +722,7 @@ def mock_server(
     port: int,
     workers: int,
     model: str,
+    processor: str | None,
     request_latency: float,
     request_latency_std: float,
     ttft_ms: float,
@@ -739,11 +741,12 @@ def mock_server(
     development scenarios requiring predictable server behavior.
     """
 
-    config = ServerConfig(
+    config = MockServerConfig(
         host=host,
         port=port,
         workers=workers,
         model=model,
+        processor=processor,
         request_latency=request_latency,
         request_latency_std=request_latency_std,
         ttft_ms=ttft_ms,

src/guidellm/mock_server/__init__.py

@@ -2,6 +2,7 @@
 GuideLLM Mock Server for OpenAI and vLLM API compatibility.
 """
 
+from .config import MockServerConfig
 from .server import MockServer
 
-__all__ = ["MockServer"]
+__all__ = ["MockServer", "MockServerConfig"]

src/guidellm/scheduler/worker.py

@@ -299,9 +299,6 @@ async def _process_next_request(self):
             request_info.scheduler_timings.resolve_end = time.time()
             self._send_update("completed", response, request, request_info)
 
-            print("\n\n********Completed request")
-            print(request_info)
-
             response = request = request_info = None
         except asyncio.CancelledError:
             # Handle cancellation

src/guidellm/scheduler/worker_group.py

@@ -479,7 +479,6 @@ def _iter():
                 scheduler_start_time=self._start_time,
             )
             _, stop = self._locked_update(request_info, source="generator")
-            print(f"----Sending request {request_info}")
             yield (request, request_info)
 
             if stop:
@@ -517,7 +516,6 @@ def update_callback_receive(
         :return: Updated tuple with injected scheduler state
         """
         response, request, request_info = update
-        print(f"\n###########Received update for request: {request_info}")
         state, stop = self._locked_update(info=request_info, source="updates")
 
         if stop: