diff --git a/deployment/tensorrt_llm/ReadMe.md b/deployment/tensorrt_llm/ReadMe.md
index 240ca94..ffc8c42 100644
--- a/deployment/tensorrt_llm/ReadMe.md
+++ b/deployment/tensorrt_llm/ReadMe.md
@@ -5,7 +5,9 @@
 ## ✅ Introduction
 The Dolphin model employs a **Swin Encoder + MBart Decoder** architecture. In the HuggingFace Transformers [Config](https://huggingface.co/ByteDance/Dolphin/blob/main/config.json), 
 its architectures field is specified as "VisionEncoderDecoderModel". Dolphin, Nougat, and Donut share the same model architecture. TensorRT-LLM has already supported the Nougat model. 
-Following Nougat's conversion script, we have successfully implemented Dolphin on TensorRT-LLM. Note: input_ids MUST be of int32 type, otherwise TensorRT-LLM will produce incorrect results.
+Following Nougat's conversion script, we have successfully implemented Dolphin on TensorRT-LLM. 
+
+**Note:** prompt_ids MUST be of **int32** type, otherwise TensorRT-LLM will produce incorrect results.
 
 ## 🛠️ Installation
 > We only test TensorRT-LLM 0.18.1 on Linux.
diff --git a/deployment/tensorrt_llm/dolphin_runner.py b/deployment/tensorrt_llm/dolphin_runner.py
index ec6da0e..6985330 100644
--- a/deployment/tensorrt_llm/dolphin_runner.py
+++ b/deployment/tensorrt_llm/dolphin_runner.py
@@ -115,8 +115,9 @@ class DolphinRunner(MultimodalModelRunner):
         prompts = [f"<s>{text.strip()} <Answer/>" for text in input_texts]
         images = self.processor(input_images, return_tensors="pt")['pixel_values'].to("cuda")
         prompt_ids = self.tokenizer(prompts, add_special_tokens=False, return_tensors="pt").input_ids.to("cuda")
-        prompt_ids = prompt_ids.to(
-            torch.int32)  # Important! If the type of prompt_ids is not int32, the output will be wrong.
+
+        # 🚨🚨🚨 Important! If the type of prompt_ids is not int32, the output will be wrong. 🚨🚨🚨
+        prompt_ids = prompt_ids.to(torch.int32)
 
         logger.info("---------------------------------------------------------")
         logger.info(f"images size: {images.size()}")