From dbba3cabb025fd05f56a7e65ddf848097f98171c Mon Sep 17 00:00:00 2001
From: zhangxinyuehfad <59153331+zhangxinyuehfad@users.noreply.github.com>
Date: Thu, 7 Aug 2025 14:08:14 +0800
Subject: [PATCH] [Doc] Update tutorials for single_npu_audio and
 single_npu_multimodal (#2252)

### What this PR does / why we need it?
Update tutorials for single_npu_audio and single_npu_multimodal

- vLLM version: v0.10.0
- vLLM main:
https://github.com/vllm-project/vllm/commit/6b47ef24de3d3b4f551aca0bc21b9f16f3d21b6a

Signed-off-by: hfadzxy <starmoon_zhang@163.com>
---
 docs/source/tutorials/single_npu_audio.md      | 1 +
 docs/source/tutorials/single_npu_multimodal.md | 2 +-
 2 files changed, 2 insertions(+), 1 deletion(-)

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