[Frontend] Automatic detection of chat content format from AST (#9919)

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

vllm/engine/llm_engine.py

@@ -262,8 +262,7 @@ class LLMEngine:
             "num_scheduler_steps=%d, chunked_prefill_enabled=%s "
             "multi_step_stream_outputs=%s, enable_prefix_caching=%s, "
             "use_async_output_proc=%s, use_cached_outputs=%s, "
-            "chat_template_text_format=%s, mm_processor_kwargs=%s, "
-            "pooler_config=%r)",
+            "mm_processor_kwargs=%s, pooler_config=%r)",
             VLLM_VERSION,
             model_config.model,
             speculative_config,
@@ -296,7 +295,6 @@ class LLMEngine:
             cache_config.enable_prefix_caching,
             model_config.use_async_output_proc,
             use_cached_outputs,
-            model_config.chat_template_text_format,
             model_config.mm_processor_kwargs,
             model_config.pooler_config,
         )