[Renderer] Consolidate factory methods (#38218)

Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>

tests/entrypoints/openai/chat_completion/test_serving_chat.py

@@ -41,7 +41,7 @@ from vllm.renderers.hf import HfRenderer
 from vllm.renderers.mistral import MistralRenderer
 from vllm.tokenizers import get_tokenizer
 from vllm.tokenizers.mistral import MistralTokenizer
-from vllm.tokenizers.registry import tokenizer_args_from_config
+from vllm.tokenizers.registry import cached_tokenizer_from_config
 from vllm.tool_parsers import ToolParserManager
 from vllm.v1.engine.async_llm import AsyncLLM
 
@@ -553,11 +553,9 @@ class MockVllmConfig:
 
 
 def _build_renderer(model_config: MockModelConfig):
-    _, tokenizer_name, _, kwargs = tokenizer_args_from_config(model_config)
-
-    return HfRenderer.from_config(
+    return HfRenderer(
         MockVllmConfig(model_config, parallel_config=MockParallelConfig()),
-        tokenizer_kwargs={**kwargs, "tokenizer_name": tokenizer_name},
+        cached_tokenizer_from_config(model_config),
     )