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

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

tests/async_engine/test_async_llm_engine.py

@@ -25,7 +25,7 @@ class MockEngine:
         return [RequestOutput(
             request_id=self.request_id)] if self.request_id else []
 
-    async def encode_request_async(self, *args, **kwargs):
+    async def process_model_inputs_async(self, *args, **kwargs):
         pass
 
     def generate(self, request_id):

tests/async_engine/test_openapi_server_ray.py

@@ -29,7 +29,7 @@ def server():
     ray.shutdown()
 
 
-@pytest.fixture(scope="session")
+@pytest.fixture(scope="module")
 def client():
     client = openai.AsyncOpenAI(
         base_url="http://localhost:8000/v1",