[Fix]fix empty prompt_token_ids,update the parser's triggering condition,add prompt log

Author: luukunn

fastdeploy/input/mm_processor/process.py

@@ -485,5 +485,5 @@ def apply_chat_template(self, request):
         tokens = self.tokenizer.tokenize(prompt_token_str)
         token_ids = self.tokenizer.convert_tokens_to_ids(tokens)
         data_processor_logger.info(
-            f"req_id:{request.get('request_id', ''),} tokens:{tokens}, token_ids: {token_ids}")
+            f"req_id:{request.get('request_id', ''),} tokens: {tokens}, token_ids: {token_ids}")
         return token_ids