[Core] Consolidate prompt arguments to LLM engines (#4328)

Co-authored-by: Roger Wang <ywang@roblox.com>

tests/entrypoints/openai/test_serving_chat.py

@@ -1,11 +1,15 @@
 import asyncio
 from dataclasses import dataclass
 
+import pytest
+
 from vllm.entrypoints.openai.serving_chat import OpenAIServingChat
 
 MODEL_NAME = "openai-community/gpt2"
 CHAT_TEMPLATE = "Dummy chat template for testing {}"
 
+pytestmark = pytest.mark.openai
+
 
 @dataclass
 class MockModelConfig: