diff --git a/docs/source/tutorials/single_npu_audio.md b/docs/source/tutorials/single_npu_audio.md
index 734e6dc..137d761 100644
--- a/docs/source/tutorials/single_npu_audio.md
+++ b/docs/source/tutorials/single_npu_audio.md
@@ -54,6 +54,7 @@ from vllm import LLM, SamplingParams
 from vllm.assets.audio import AudioAsset
 from vllm.utils import FlexibleArgumentParser
 
+# If network issues prevent AudioAsset from fetching remote audio files, retry or check your network.
 audio_assets = [AudioAsset("mary_had_lamb"), AudioAsset("winning_call")]
 question_per_audio_count = {
     1: "What is recited in the audio?",
diff --git a/docs/source/tutorials/single_npu_multimodal.md b/docs/source/tutorials/single_npu_multimodal.md
index 8c19651..a678ec7 100644
--- a/docs/source/tutorials/single_npu_multimodal.md
+++ b/docs/source/tutorials/single_npu_multimodal.md
@@ -43,7 +43,7 @@ export PYTORCH_NPU_ALLOC_CONF=max_split_size_mb:256
 Run the following script to execute offline inference on a single NPU:
 
 ```bash
-pip install torchvision==0.20.1 qwen_vl_utils --extra-index-url https://download.pytorch.org/whl/cpu/
+pip install qwen_vl_utils --extra-index-url https://download.pytorch.org/whl/cpu/
 ```
 
 ```python