[Feature] Support output modalities control per request (#298)

Signed-off-by: Gaohan123 <hgaoaf@connect.ust.hk>

docs/user_guide/examples/offline_inference/qwen2_5_omni.md

@@ -38,6 +38,14 @@ Then run the command below.
 bash run_single_prompt.sh
 ```
 
+### Modality control
+If you want to control output modalities, e.g. only output text, you can run the command below:
+```bash
+python end2end.py --output-wav output_audio \
+                  --query-type mixed_modalities \
+                  --modalities text
+```
+
 #### Using Local Media Files
 The `end2end.py` script supports local media files (audio, video, image) via CLI arguments:
 

docs/user_guide/examples/offline_inference/qwen3_omni.md

@@ -33,6 +33,14 @@ If you have not enough memory, you can set thinker with tensor parallel. Just ru
 bash run_single_prompt_tp.sh
 ```
 
+### Modality control
+If you want to control output modalities, e.g. only output text, you can run the command below:
+```bash
+python end2end.py --output-wav output_audio \
+                  --query-type use_audio \
+                  --modalities text
+```
+
 #### Using Local Media Files
 The `end2end.py` script supports local media files (audio, video, image) via command-line arguments: