[Docs][skip ci] Fix omni and tts docs (#2130)

Signed-off-by: gcanlin <canlinguosdu@gmail.com>

docs/getting_started/installation/npu/npu.inc.md

@@ -73,7 +73,6 @@ cd /vllm-workspace/vllm
 git pull origin main
 git fetch origin --tags
 git checkout v0.18.0
-VLLM_TARGET_DEVICE=empty pip install -v -e .
 
 # Because vllm-ascend has not yet entered continuous development and has not been officially released, we need to pin it to a specific commit. Please note that this commit may change over time.
 cd /vllm-workspace/vllm-ascend
@@ -83,8 +82,8 @@ git checkout 1e05c4908f31737bc4eef865a9f351d030a77c9d
 pip install -v -e .
 
 # Install vLLM-Omni from the latest main branch
-cd /vllm-workspace/vllm-omni
 git clone https://github.com/vllm-project/vllm-omni.git
+cd /vllm-workspace/vllm-omni
 pip install -v -e . --no-build-isolation
 # or VLLM_OMNI_TARGET_DEVICE=npu pip install -v -e .
 export VLLM_WORKER_MULTIPROC_METHOD=spawn

examples/online_serving/qwen3_omni/README.md

@@ -15,7 +15,7 @@ vllm serve Qwen/Qwen3-Omni-30B-A3B-Instruct --omni --port 8091
 If you want to open async chunking for qwen3-omni, launch the server with command below
 
 ```bash
-vllm serve Qwen/Qwen3-Omni-30B-A3B-Instruct --omni --port 8091 --stage-configs-path /vllm_omni/model_executor/stage_configs/qwen3_omni_moe_async_chunk.yaml
+vllm serve Qwen/Qwen3-Omni-30B-A3B-Instruct --omni --port 8091 --stage-configs-path vllm_omni/model_executor/stage_configs/qwen3_omni_moe_async_chunk.yaml
 ```
 
 If you have custom stage configs file, launch the server with command below
@@ -79,7 +79,7 @@ You can control output modalities to specify which types of output the model sho
 | Modalities | Output |
 |------------|--------|
 | `["text"]` | Text only |
-| `["audio"]` | Text + Audio |
+| `["audio"]` | Audio only |
 | `["text", "audio"]` | Text + Audio |
 | Not specified | Text + Audio (default) |
 
@@ -100,13 +100,13 @@ curl http://localhost:8091/v1/chat/completions \
 #### Text + Audio
 
 ```bash
-curl http://localhost:8091/v1/chat/completions \
+curl -s http://localhost:8091/v1/chat/completions \
   -H "Content-Type: application/json" \
   -d '{
     "model": "Qwen/Qwen3-Omni-30B-A3B-Instruct",
     "messages": [{"role": "user", "content": "Describe vLLM in brief."}],
     "modalities": ["audio"]
-  }'
+  }' | jq -r '.choices[0].message.audio.data' | base64 -d > output.wav
 ```
 
 ### Using Python client
@@ -137,6 +137,7 @@ print(response.choices[0].message.content)
 #### Text + Audio
 
 ```python
+import base64
 from openai import OpenAI
 
 client = OpenAI(base_url="http://localhost:8091/v1", api_key="EMPTY")
@@ -144,11 +145,15 @@ client = OpenAI(base_url="http://localhost:8091/v1", api_key="EMPTY")
 response = client.chat.completions.create(
     model="Qwen/Qwen3-Omni-30B-A3B-Instruct",
     messages=[{"role": "user", "content": "Describe vLLM in brief."}],
-    modalities=["audio"]
+    modalities=["text", "audio"]
 )
 # Response contains two choices: one with text, one with audio
 print(response.choices[0].message.content)  # Text response
-print(response.choices[1].message.audio)    # Audio response
+
+# Save audio to file
+audio_data = base64.b64decode(response.choices[1].message.audio.data)
+with open("output.wav", "wb") as f:
+    f.write(audio_data)
 ```
 
 ## Speaker selection

examples/online_serving/qwen3_tts/README.md

@@ -43,30 +43,23 @@ Then open http://localhost:7860 in your browser.
 
 ### Launch the Server
 
+The default stage config is located at `vllm_omni/model_executor/stage_configs/qwen3_tts.yaml`. For other platforms (e.g., NPU), refer to `vllm_omni/platforms/npu/stage_configs/qwen3_tts.yaml`.
+
 ```bash
 # CustomVoice model (predefined speakers)
 vllm serve Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice \
-    --stage-configs-path vllm_omni/model_executor/stage_configs/qwen3_tts.yaml \
     --omni \
-    --port 8091 \
+    --port 8091
-    --trust-remote-code \
-    --enforce-eager
 
 # VoiceDesign model
 vllm serve Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign \
-    --stage-configs-path vllm_omni/model_executor/stage_configs/qwen3_tts.yaml \
     --omni \
-    --port 8091 \
+    --port 8091
-    --trust-remote-code \
-    --enforce-eager
 
 # Base model (voice cloning)
 vllm serve Qwen/Qwen3-TTS-12Hz-1.7B-Base \
-    --stage-configs-path vllm_omni/model_executor/stage_configs/qwen3_tts.yaml \
     --omni \
-    --port 8091 \
+    --port 8091
-    --trust-remote-code \
-    --enforce-eager
 ```
 
 If you have custom stage configs file, launch the server with command below
@@ -74,9 +67,7 @@ If you have custom stage configs file, launch the server with command below
 vllm serve Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice \
     --stage-configs-path /path/to/stage_configs_file \
     --omni \
-    --port 8091 \
+    --port 8091
-    --trust-remote-code \
-    --enforce-eager
 ```
 
 Alternatively, use the convenience script:
@@ -99,12 +90,14 @@ cd examples/online_serving/qwen3_tts
 ```bash
 # CustomVoice: Use predefined speaker
 python openai_speech_client.py \
+    --model Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice \
     --text "你好，我是通义千问" \
     --voice vivian \
     --language Chinese
 
 # CustomVoice with style instruction
 python openai_speech_client.py \
+    --model Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice \
     --text "今天天气真好" \
     --voice ryan \
     --instructions "用开心的语气说"