[Feature]Basic version of supporting streaming output

docs/api/README.md

@@ -32,6 +32,7 @@ Input data structures for multi-modal inputs.
 
 Engine classes for offline and online inference.
 
+- [vllm_omni.diffusion.diffusion_engine.BackgroundResources][]
 - [vllm_omni.diffusion.diffusion_engine.DiffusionEngine][]
 - [vllm_omni.engine.AdditionalInformationEntry][]
 - [vllm_omni.engine.AdditionalInformationPayload][]
@@ -57,6 +58,7 @@ Core scheduling and caching components.
 
 Model execution components.
 
+- [vllm_omni.model_executor.custom_process_mixin.CustomProcessMixin][]
 - [vllm_omni.model_executor.models.output_templates.OmniOutput][]
 - [vllm_omni.model_executor.models.qwen2_5_omni.qwen2_5_omni.Qwen2_5OmniForConditionalGeneration][]
 - [vllm_omni.model_executor.models.qwen2_5_omni.qwen2_5_omni_talker.Qwen2_5OmniTalkerForConditionalGeneration][]

docs/user_guide/examples/online_serving/qwen2_5_omni.md

@@ -74,84 +74,19 @@ bash run_curl_multimodal_generation.sh mixed_modalities
 ```
 
 ## Modality control
-
-You can control output modalities to specify which types of output the model should generate. This is useful when you only need text output and want to skip audio generation stages for better performance.
-
-### Supported modalities
-
-| Modalities | Output |
-|------------|--------|
-| `["text"]` | Text only |
-| `["audio"]` | Text + Audio |
-| `["text", "audio"]` | Text + Audio |
-| Not specified | Text + Audio (default) |
-
-### Using curl
-
-#### Text only
-
-```bash
-curl http://localhost:8091/v1/chat/completions \
-  -H "Content-Type: application/json" \
-  -d '{
-    "model": "Qwen/Qwen2.5-Omni-7B",
-    "messages": [{"role": "user", "content": "Describe vLLM in brief."}],
-    "modalities": ["text"]
-  }'
-```
-
-#### Text + Audio
-
-```bash
-curl http://localhost:8091/v1/chat/completions \
-  -H "Content-Type: application/json" \
-  -d '{
-    "model": "Qwen/Qwen2.5-Omni-7B",
-    "messages": [{"role": "user", "content": "Describe vLLM in brief."}],
-    "modalities": ["audio"]
-  }'
-```
-
-### Using Python client
-
+If you want to control output modalities, e.g. only output text, you can run the command below:
 ```bash
 python openai_chat_completion_client_for_multimodal_generation.py \
     --query-type mixed_modalities \
     --modalities text
 ```
 
-### Using OpenAI Python SDK
-
-#### Text only
-
-```python
-from openai import OpenAI
-
-client = OpenAI(base_url="http://localhost:8091/v1", api_key="EMPTY")
-
-response = client.chat.completions.create(
-    model="Qwen/Qwen2.5-Omni-7B",
-    messages=[{"role": "user", "content": "Describe vLLM in brief."}],
-    modalities=["text"]
-)
-print(response.choices[0].message.content)
-```
-
-#### Text + Audio
-
-```python
-from openai import OpenAI
-
-client = OpenAI(base_url="http://localhost:8091/v1", api_key="EMPTY")
-
-response = client.chat.completions.create(
-    model="Qwen/Qwen2.5-Omni-7B",
-    messages=[{"role": "user", "content": "Describe vLLM in brief."}],
-    modalities=["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
+## Streaming Output
+If you want to enable streaming output, please set the argument as below. The final output will be obtained just after generated by corresponding stage. Now we only support text streaming output. Other modalities can output normally.
+```bash
+python openai_chat_completion_client_for_multimodal_generation.py \
+    --query-type mixed_modalities \
+    --stream
 ```
 
 ## Run Local Web UI Demo

docs/user_guide/examples/online_serving/qwen3_omni.md

@@ -82,84 +82,19 @@ sudo apt install ffmpeg
 ```
 
 ## Modality control
-
-You can control output modalities to specify which types of output the model should generate. This is useful when you only need text output and want to skip audio generation stages for better performance.
-
-### Supported modalities
-
-| Modalities | Output |
-|------------|--------|
-| `["text"]` | Text only |
-| `["audio"]` | Text + Audio |
-| `["text", "audio"]` | Text + Audio |
-| Not specified | Text + Audio (default) |
-
-### Using curl
-
-#### Text only
-
-```bash
-curl 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": ["text"]
-  }'
-```
-
-#### Text + Audio
-
-```bash
-curl 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"]
-  }'
-```
-
-### Using Python client
-
+If you want to control output modalities, e.g. only output text, you can run the command below:
 ```bash
 python openai_chat_completion_client_for_multimodal_generation.py \
     --query-type use_image \
     --modalities text
 ```
 
-### Using OpenAI Python SDK
-
-#### Text only
-
-```python
-from openai import OpenAI
-
-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=["text"]
-)
-print(response.choices[0].message.content)
-```
-
-#### Text + Audio
-
-```python
-from openai import OpenAI
-
-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"]
-)
-# 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
+## Streaming Output
+If you want to enable streaming output, please set the argument as below. The final output will be obtained just after generated by corresponding stage. Now we only support text streaming output. Other modalities can output normally.
+```bash
+python openai_chat_completion_client_for_multimodal_generation.py \
+    --query-type use_image \
+    --stream
 ```
 
 ## Run Local Web UI Demo

examples/offline_inference/qwen2_5_omni/end2end.py

@@ -377,12 +377,12 @@ def main(args):
         for i, prompt in enumerate(prompts):
             prompt["modalities"] = output_modalities
 
-    omni_outputs = omni_llm.generate(prompts, sampling_params_list)
+    omni_generator = omni_llm.generate(prompts, sampling_params_list)
 
     # Determine output directory: prefer --output-dir; fallback to --output-wav
     output_dir = args.output_dir if getattr(args, "output_dir", None) else args.output_wav
     os.makedirs(output_dir, exist_ok=True)
-    for stage_outputs in omni_outputs:
+    for stage_outputs in omni_generator:
         if stage_outputs.final_output_type == "text":
             for output in stage_outputs.request_output:
                 request_id = output.request_id

examples/offline_inference/qwen3_omni/end2end.py

@@ -233,12 +233,12 @@ def main(args):
         for i, prompt in enumerate(prompts):
             prompt["modalities"] = output_modalities
 
-    omni_outputs = omni_llm.generate(prompts, sampling_params_list)
+    omni_generator = omni_llm.generate(prompts, sampling_params_list)
     # Determine output directory: prefer --output-dir; fallback to --output-wav
     output_dir = args.output_dir if getattr(args, "output_dir", None) else args.output_wav
     os.makedirs(output_dir, exist_ok=True)
 
-    for stage_outputs in omni_outputs:
+    for stage_outputs in omni_generator:
         if stage_outputs.final_output_type == "text":
             for output in stage_outputs.request_output:
                 request_id = output.request_id

examples/online_serving/qwen2_5_omni/README.md

@@ -78,6 +78,14 @@ python openai_chat_completion_client_for_multimodal_generation.py \
     --modalities text
 ```
 
+## Streaming Output
+If you want to enable streaming output, please set the argument as below. The final output will be obtained just after generated by corresponding stage. Now we only support text streaming output. Other modalities can output normally.
+```bash
+python openai_chat_completion_client_for_multimodal_generation.py \
+    --query-type mixed_modalities \
+    --stream
+```
+
 ## Run Local Web UI Demo
 
 This Web UI demo allows users to interact with the model through a web browser.