diff --git a/docs/user_guide/examples/offline_inference/mimo_audio.md b/docs/user_guide/examples/offline_inference/mimo_audio.md
index 6af7bc72e..1a3be15d6 100644
--- a/docs/user_guide/examples/offline_inference/mimo_audio.md
+++ b/docs/user_guide/examples/offline_inference/mimo_audio.md
@@ -13,7 +13,7 @@ MiMo-Audio provides multiple task variants for audio understanding and generatio
 - **tts_sft_with_instruct**: TTS generation with explicit voice style instructions.
 - **tts_sft_with_audio**: TTS generation with audio reference for voice cloning.
 - **tts_sft_with_natural_instruction**: TTS generation from natural language descriptions embedded in text.
-- **audio_trancribing_sft**: Transcribe audio to text (speech-to-text).
+- **audio_trancribing_sft**: Transcribe audio to text (speech-to-text). (note: the upstream task name uses the spelling 'trancribing', don't fix it)
 - **audio_understanding_sft**: Understand and analyze audio content with text queries.
 - **audio_understanding_sft_with_thinking**: Audio understanding with reasoning chain.
 - **spoken_dialogue_sft_multiturn**: Multi-turn spoken dialogue with audio input/output.
diff --git a/docs/user_guide/examples/offline_inference/qwen3_tts.md b/docs/user_guide/examples/offline_inference/qwen3_tts.md
index 15a5fac23..19fea4132 100644
--- a/docs/user_guide/examples/offline_inference/qwen3_tts.md
+++ b/docs/user_guide/examples/offline_inference/qwen3_tts.md
@@ -11,7 +11,7 @@ Qwen3 TTS provides multiple task variants for speech generation:
 
 - **CustomVoice**: Generate speech with a known speaker identity (speaker ID) and optional instruction.
 - **VoiceDesign**: Generate speech from text plus a descriptive instruction that designs a new voice.
-- **Base**: Voice cloning using a reference audio + reference transcript, with optional mode selection.
+- **Base**: Voice cloning using a reference audio + reference transcript, with optional mode selection. The `ref_audio` field accepts a local file path, HTTP URL, or base64 data URL.
 
 ## Setup
 Please refer to the [stage configuration documentation](https://docs.vllm.ai/projects/vllm-omni/en/latest/configuration/stage_configs/) to configure memory allocation appropriately for your hardware setup.
diff --git a/docs/user_guide/examples/online_serving/qwen3_tts.md b/docs/user_guide/examples/online_serving/qwen3_tts.md
index 65023258e..ee293131d 100644
--- a/docs/user_guide/examples/online_serving/qwen3_tts.md
+++ b/docs/user_guide/examples/online_serving/qwen3_tts.md
@@ -21,10 +21,10 @@ Please refer to [README.md](https://github.com/vllm-project/vllm-omni/tree/main/
 
 Two interactive Gradio demos are available, both supporting all 3 task types:
 
-| Demo | File | Transport | Streaming Quality |
-| ---- | ---- | --------- | ----------------- |
-| Standard | `gradio_demo.py` | HTTP chunked | May have small gaps between chunks |
-| FastRTC | `gradio_fastrtc_demo.py` | WebRTC | Gapless streaming (requires `pip install fastrtc`) |
+| Demo     | File                     | Transport    | Streaming Quality                                  |
+| -------- | ------------------------ | ------------ | -------------------------------------------------- |
+| Standard | `gradio_demo.py`         | HTTP chunked | May have small gaps between chunks                 |
+| FastRTC  | `gradio_fastrtc_demo.py` | WebRTC       | Gapless streaming (requires `pip install fastrtc`) |
 
 ```bash
 # Option 1: Launch server + Standard Gradio together
@@ -137,8 +137,8 @@ The Python client supports the following command-line arguments:
 - `--speaker`: Speaker name (default: `vivian`). Options: `vivian`, `ryan`, `aiden`, etc.
 - `--language`: Language. Options: `Auto`, `Chinese`, `English`, `Japanese`, `Korean`, `German`, `French`, `Russian`, `Portuguese`, `Spanish`, `Italian`
 - `--instructions`: Voice style/emotion instructions
-- `--ref-audio`: Reference audio file path or URL for voice cloning (Base task)
-- `--ref-text`: Reference audio transcript for voice cloning (Base task)
+- `--ref-audio`: Reference audio file path or URL for voice cloning (Base task). Local paths are automatically base64-encoded by the client before sending to the server.
+- `--ref-text`: Reference audio transcript for voice cloning (Base task).
 - `--response-format`: Audio output format (default: `wav`). Options: `wav`, `mp3`, `flac`, `pcm`, `aac`, `opus`
 - `--output` (or `-o`): Output audio file path (default: `tts_output.wav`)
 
@@ -284,7 +284,7 @@ This endpoint follows the [OpenAI Audio Speech API](https://platform.openai.com/
     "task_type": "CustomVoice",
     "language": "Auto",
     "instructions": "Optional style instructions",
-    "ref_audio": "URL or base64 for voice cloning",
+    "ref_audio":  "HTTP URL, base64 data URL, or file:// URI for voice cloning",
     "ref_text": "Reference audio transcript",
     "x_vector_only_mode": false,
     "max_new_tokens": 2048
@@ -317,24 +317,24 @@ Returns binary audio data with appropriate `Content-Type` header (e.g., `audio/w
 
 ### vLLM-Omni Extension Parameters
 
-| Parameter        | Type   | Default       | Description                                                                  |
-| ---------------- | ------ | ------------- | ---------------------------------------------------------------------------- |
-| `task_type`      | string | "CustomVoice" | Task: CustomVoice, VoiceDesign, or Base                                      |
-| `language`       | string | "Auto"        | Language (see supported languages below)                                     |
-| `instructions`   | string | ""            | Voice style/emotion instructions                                             |
-| `max_new_tokens` | int    | 2048          | Maximum tokens to generate                                                   |
-| `initial_codec_chunk_frames` | int | null | Per-request initial chunk size override for TTFA tuning. When null, IC is computed dynamically based on server load. |
-| `stream`         | bool   | false         | Stream raw PCM chunks as they are decoded (requires `response_format="pcm"`) |
+| Parameter                    | Type   | Default       | Description                                                                                                          |
+| ---------------------------- | ------ | ------------- | -------------------------------------------------------------------------------------------------------------------- |
+| `task_type`                  | string | "CustomVoice" | Task: CustomVoice, VoiceDesign, or Base                                                                              |
+| `language`                   | string | "Auto"        | Language (see supported languages below)                                                                             |
+| `instructions`               | string | ""            | Voice style/emotion instructions                                                                                     |
+| `max_new_tokens`             | int    | 2048          | Maximum tokens to generate                                                                                           |
+| `initial_codec_chunk_frames` | int    | null          | Per-request initial chunk size override for TTFA tuning. When null, IC is computed dynamically based on server load. |
+| `stream`                     | bool   | false         | Stream raw PCM chunks as they are decoded (requires `response_format="pcm"`)                                         |
 
 **Supported languages:** Auto, Chinese, English, Japanese, Korean, German, French, Russian, Portuguese, Spanish, Italian
 
 ### Voice Clone Parameters (Base task)
 
-| Parameter            | Type   | Required | Description                                  |
-| -------------------- | ------ | -------- | -------------------------------------------- |
-| `ref_audio`          | string | **Yes**  | Reference audio (URL or base64 data URL)     |
-| `ref_text`           | string | No       | Transcript of reference audio (for ICL mode) |
-| `x_vector_only_mode` | bool   | No       | Use speaker embedding only (no ICL)          |
+| Parameter            | Type   | Required | Description                                                                                     |
+| -------------------- | ------ | -------- | ----------------------------------------------------------------------------------------------- |
+| `ref_audio`          | string | **Yes**  | Reference audio (HTTP URL, base64 data URL, or `file://` URI with `--allowed-local-media-path`) |
+| `ref_text`           | string | No       | Transcript of reference audio (for ICL mode)                                                    |
+| `x_vector_only_mode` | bool   | No       | Use speaker embedding only (no ICL)                                                             |
 
 ## Streaming
 
diff --git a/docs/user_guide/examples/online_serving/text_to_image.md b/docs/user_guide/examples/online_serving/text_to_image.md
index be8c7d894..39be6e5f0 100644
--- a/docs/user_guide/examples/online_serving/text_to_image.md
+++ b/docs/user_guide/examples/online_serving/text_to_image.md
@@ -23,6 +23,29 @@ Or use the startup script:
 bash run_server.sh
 ```
 
+### Start with Parallelism Acceleration
+
+Enable Tensor Parallelism and VAE Patch Parallelism for faster inference:
+
+```bash
+# With Tensor Parallelism (requires >= 2 GPUs)
+vllm serve Qwen/Qwen-Image --omni --port 8091 --tensor-parallel-size 2
+
+# With Tensor Parallelism and VAE Patch Parallelism (requires >= 2 GPUs)
+vllm serve Qwen/Qwen-Image --omni --port 8091 --tensor-parallel-size 2 --vae-patch-parallel-size 2 --vae-use-tiling
+
+# With Sequence Parallelism (Ulysses-SP, requires >= 2 GPUs)
+vllm serve Qwen/Qwen-Image --omni --port 8091 --usp 2
+
+# With Ring-Attention (requires >= 2 GPUs)
+vllm serve Qwen/Qwen-Image --omni --port 8091 --ring 2
+
+# Combined: Ulysses + Ring (requires >= 4 GPUs)
+vllm serve Qwen/Qwen-Image --omni --port 8091 --usp 2 --ring 2
+```
+
+For more details on parallelism acceleration, see the [Parallelism Acceleration Guide](https://github.com/vllm-project/vllm-omni/tree/main/examples/diffusion/parallelism_acceleration.md).
+
 ## API Calls
 
 ### Method 1: Using curl
@@ -97,12 +120,12 @@ curl -X POST http://localhost:8091/v1/images/generations \
 
 ### LoRA Parameters
 
-| Parameter     | Type   | Description                                                      |
-| ------------- | ------ | ---------------------------------------------------------------- |
-| `name`        | str    | LoRA adapter name (optional, defaults to path stem)              |
-| `local_path`  | str    | Server-local path to LoRA adapter folder (PEFT format, required) |
-| `scale`       | float  | LoRA scale factor (default: 1.0)                                 |
-| `int_id`     | int    | LoRA integer ID for caching (optional, derived from path if not provided) |
+| Parameter    | Type  | Description                                                               |
+| ------------ | ----- | ------------------------------------------------------------------------- |
+| `name`       | str   | LoRA adapter name (optional, defaults to path stem)                       |
+| `local_path` | str   | Server-local path to LoRA adapter folder (PEFT format, required)          |
+| `scale`      | float | LoRA scale factor (default: 1.0)                                          |
+| `int_id`     | int   | LoRA integer ID for caching (optional, derived from path if not provided) |
 
 ### LoRA Adapter Format
 
@@ -162,16 +185,16 @@ Use `extra_body` to pass generation parameters:
 
 ## Generation Parameters (extra_body)
 
-| Parameter                | Type  | Default | Description                    |
-| ------------------------ | ----- | ------- | ------------------------------ |
-| `height`                 | int   | None    | Image height in pixels         |
-| `width`                  | int   | None    | Image width in pixels          |
-| `size`                   | str   | None    | Image size (e.g., "1024x1024") |
-| `num_inference_steps`    | int   | 50      | Number of denoising steps      |
-| `true_cfg_scale`         | float | 4.0     | Qwen-Image CFG scale           |
-| `seed`                   | int   | None    | Random seed (reproducible)     |
-| `negative_prompt`        | str   | None    | Negative prompt                |
-| `num_outputs_per_prompt` | int   | 1       | Number of images to generate   |
+| Parameter                | Type  | Default | Description                        |
+| ------------------------ | ----- | ------- | ---------------------------------- |
+| `height`                 | int   | None    | Image height in pixels             |
+| `width`                  | int   | None    | Image width in pixels              |
+| `size`                   | str   | None    | Image size (e.g., "1024x1024")     |
+| `num_inference_steps`    | int   | 50      | Number of denoising steps          |
+| `true_cfg_scale`         | float | 4.0     | Qwen-Image CFG scale               |
+| `seed`                   | int   | None    | Random seed (reproducible)         |
+| `negative_prompt`        | str   | None    | Negative prompt                    |
+| `num_outputs_per_prompt` | int   | 1       | Number of images to generate       |
 | `--cfg-parallel-size`.   | int   | 1       | Number of GPUs for CFG parallelism |
 
 ## Response Format
diff --git a/examples/offline_inference/mimo_audio/README.md b/examples/offline_inference/mimo_audio/README.md
index dd5f87217..55f7dca0f 100644
--- a/examples/offline_inference/mimo_audio/README.md
+++ b/examples/offline_inference/mimo_audio/README.md
@@ -10,7 +10,7 @@ MiMo-Audio provides multiple task variants for audio understanding and generatio
 - **tts_sft_with_instruct**: TTS generation with explicit voice style instructions.
 - **tts_sft_with_audio**: TTS generation with audio reference for voice cloning.
 - **tts_sft_with_natural_instruction**: TTS generation from natural language descriptions embedded in text.
-- **audio_trancribing_sft**: Transcribe audio to text (speech-to-text).
+- **audio_trancribing_sft**: Transcribe audio to text (speech-to-text). (note: the upstream task name uses the spelling 'trancribing', don't fix it)
 - **audio_understanding_sft**: Understand and analyze audio content with text queries.
 - **audio_understanding_sft_with_thinking**: Audio understanding with reasoning chain.
 - **spoken_dialogue_sft_multiturn**: Multi-turn spoken dialogue with audio input/output.
diff --git a/examples/offline_inference/qwen3_tts/README.md b/examples/offline_inference/qwen3_tts/README.md
index 90a2541bc..bf59dc9ba 100644
--- a/examples/offline_inference/qwen3_tts/README.md
+++ b/examples/offline_inference/qwen3_tts/README.md
@@ -8,7 +8,7 @@ Qwen3 TTS provides multiple task variants for speech generation:
 
 - **CustomVoice**: Generate speech with a known speaker identity (speaker ID) and optional instruction.
 - **VoiceDesign**: Generate speech from text plus a descriptive instruction that designs a new voice.
-- **Base**: Voice cloning using a reference audio + reference transcript, with optional mode selection.
+- **Base**: Voice cloning using a reference audio + reference transcript, with optional mode selection. The `ref_audio` field accepts a local file path, HTTP URL, or base64 data URL.
 
 ## Setup
 Please refer to the [stage configuration documentation](https://docs.vllm.ai/projects/vllm-omni/en/latest/configuration/stage_configs/) to configure memory allocation appropriately for your hardware setup.
diff --git a/examples/online_serving/qwen3_tts/README.md b/examples/online_serving/qwen3_tts/README.md
index 4709c9d42..3718f8e59 100644
--- a/examples/online_serving/qwen3_tts/README.md
+++ b/examples/online_serving/qwen3_tts/README.md
@@ -18,10 +18,10 @@ Please refer to [README.md](https://github.com/vllm-project/vllm-omni/tree/main/
 
 Two interactive Gradio demos are available, both supporting all 3 task types:
 
-| Demo | File | Transport | Streaming Quality |
-| ---- | ---- | --------- | ----------------- |
-| Standard | `gradio_demo.py` | HTTP chunked | May have small gaps between chunks |
-| FastRTC | `gradio_fastrtc_demo.py` | WebRTC | Gapless streaming (requires `pip install fastrtc`) |
+| Demo     | File                     | Transport    | Streaming Quality                                  |
+| -------- | ------------------------ | ------------ | -------------------------------------------------- |
+| Standard | `gradio_demo.py`         | HTTP chunked | May have small gaps between chunks                 |
+| FastRTC  | `gradio_fastrtc_demo.py` | WebRTC       | Gapless streaming (requires `pip install fastrtc`) |
 
 ```bash
 # Option 1: Launch server + Standard Gradio together
@@ -134,8 +134,8 @@ The Python client supports the following command-line arguments:
 - `--voice`: Speaker/voice name (default: `vivian`). Options: `vivian`, `ryan`, `aiden`, etc.
 - `--language`: Language. Options: `Auto`, `Chinese`, `English`, `Japanese`, `Korean`, `German`, `French`, `Russian`, `Portuguese`, `Spanish`, `Italian`
 - `--instructions`: Voice style/emotion instructions
-- `--ref-audio`: Reference audio file path or URL for voice cloning (Base task)
-- `--ref-text`: Reference audio transcript for voice cloning (Base task)
+- `--ref-audio`: Reference audio file path or URL for voice cloning (Base task). Local paths are automatically base64-encoded by the client before sending to the server.
+- `--ref-text`: Reference audio transcript for voice cloning (Base task).
 - `--response-format`: Audio output format (default: `wav`). Options: `wav`, `mp3`, `flac`, `pcm`, `aac`, `opus`
 - `--output` (or `-o`): Output audio file path (default: `tts_output.wav`)
 
@@ -281,7 +281,7 @@ This endpoint follows the [OpenAI Audio Speech API](https://platform.openai.com/
     "task_type": "CustomVoice",
     "language": "Auto",
     "instructions": "Optional style instructions",
-    "ref_audio": "URL or base64 for voice cloning",
+    "ref_audio":  "HTTP URL, base64 data URL, or file:// URI for voice cloning",
     "ref_text": "Reference audio transcript",
     "x_vector_only_mode": false,
     "max_new_tokens": 2048
@@ -308,24 +308,24 @@ Returns binary audio data with appropriate `Content-Type` header (e.g., `audio/w
 
 ### vLLM-Omni Extension Parameters
 
-| Parameter        | Type   | Default       | Description                                                                  |
-| ---------------- | ------ | ------------- | ---------------------------------------------------------------------------- |
-| `task_type`      | string | "CustomVoice" | Task: CustomVoice, VoiceDesign, or Base                                      |
-| `language`       | string | "Auto"        | Language (see supported languages below)                                     |
-| `instructions`   | string | ""            | Voice style/emotion instructions                                             |
-| `max_new_tokens` | int    | 2048          | Maximum tokens to generate                                                   |
-| `initial_codec_chunk_frames` | int | null | Per-request initial chunk size override for TTFA tuning. When null, IC is computed dynamically based on server load. |
-| `stream`         | bool   | false         | Stream raw PCM chunks as they are decoded (requires `response_format="pcm"`) |
+| Parameter                    | Type   | Default       | Description                                                                                                          |
+| ---------------------------- | ------ | ------------- | -------------------------------------------------------------------------------------------------------------------- |
+| `task_type`                  | string | "CustomVoice" | Task: CustomVoice, VoiceDesign, or Base                                                                              |
+| `language`                   | string | "Auto"        | Language (see supported languages below)                                                                             |
+| `instructions`               | string | ""            | Voice style/emotion instructions                                                                                     |
+| `max_new_tokens`             | int    | 2048          | Maximum tokens to generate                                                                                           |
+| `initial_codec_chunk_frames` | int    | null          | Per-request initial chunk size override for TTFA tuning. When null, IC is computed dynamically based on server load. |
+| `stream`                     | bool   | false         | Stream raw PCM chunks as they are decoded (requires `response_format="pcm"`)                                         |
 
 **Supported languages:** Auto, Chinese, English, Japanese, Korean, German, French, Russian, Portuguese, Spanish, Italian
 
 ### Voice Clone Parameters (Base task)
 
-| Parameter            | Type   | Required | Description                                  |
-| -------------------- | ------ | -------- | -------------------------------------------- |
-| `ref_audio`          | string | **Yes**  | Reference audio (URL or base64 data URL)     |
-| `ref_text`           | string | No       | Transcript of reference audio (for ICL mode) |
-| `x_vector_only_mode` | bool   | No       | Use speaker embedding only (no ICL)          |
+| Parameter            | Type   | Required | Description                                                                                     |
+| -------------------- | ------ | -------- | ----------------------------------------------------------------------------------------------- |
+| `ref_audio`          | string | **Yes**  | Reference audio (HTTP URL, base64 data URL, or `file://` URI with `--allowed-local-media-path`) |
+| `ref_text`           | string | No       | Transcript of reference audio (for ICL mode)                                                    |
+| `x_vector_only_mode` | bool   | No       | Use speaker embedding only (no ICL)                                                             |
 
 ## Streaming
 
diff --git a/examples/online_serving/text_to_image/README.md b/examples/online_serving/text_to_image/README.md
index 140036d00..52091045f 100644
--- a/examples/online_serving/text_to_image/README.md
+++ b/examples/online_serving/text_to_image/README.md
@@ -20,6 +20,29 @@ Or use the startup script:
 bash run_server.sh
 ```
 
+### Start with Parallelism Acceleration
+
+Enable Tensor Parallelism and VAE Patch Parallelism for faster inference:
+
+```bash
+# With Tensor Parallelism (requires >= 2 GPUs)
+vllm serve Qwen/Qwen-Image --omni --port 8091 --tensor-parallel-size 2
+
+# With Tensor Parallelism and VAE Patch Parallelism (requires >= 2 GPUs)
+vllm serve Qwen/Qwen-Image --omni --port 8091 --tensor-parallel-size 2 --vae-patch-parallel-size 2 --vae-use-tiling
+
+# With Sequence Parallelism (Ulysses-SP, requires >= 2 GPUs)
+vllm serve Qwen/Qwen-Image --omni --port 8091 --usp 2
+
+# With Ring-Attention (requires >= 2 GPUs)
+vllm serve Qwen/Qwen-Image --omni --port 8091 --ring 2
+
+# Combined: Ulysses + Ring (requires >= 4 GPUs)
+vllm serve Qwen/Qwen-Image --omni --port 8091 --usp 2 --ring 2
+```
+
+For more details on parallelism acceleration, see the [Parallelism Acceleration Guide](../../diffusion/parallelism_acceleration.md).
+
 ## API Calls
 
 ### Method 1: Using curl
@@ -94,12 +117,12 @@ curl -X POST http://localhost:8091/v1/images/generations \
 
 ### LoRA Parameters
 
-| Parameter     | Type   | Description                                                      |
-| ------------- | ------ | ---------------------------------------------------------------- |
-| `name`        | str    | LoRA adapter name (optional, defaults to path stem)              |
-| `local_path`  | str    | Server-local path to LoRA adapter folder (PEFT format, required) |
-| `scale`       | float  | LoRA scale factor (default: 1.0)                                 |
-| `int_id`     | int    | LoRA integer ID for caching (optional, derived from path if not provided) |
+| Parameter    | Type  | Description                                                               |
+| ------------ | ----- | ------------------------------------------------------------------------- |
+| `name`       | str   | LoRA adapter name (optional, defaults to path stem)                       |
+| `local_path` | str   | Server-local path to LoRA adapter folder (PEFT format, required)          |
+| `scale`      | float | LoRA scale factor (default: 1.0)                                          |
+| `int_id`     | int   | LoRA integer ID for caching (optional, derived from path if not provided) |
 
 ### LoRA Adapter Format
 
@@ -159,16 +182,16 @@ Use `extra_body` to pass generation parameters:
 
 ## Generation Parameters (extra_body)
 
-| Parameter                | Type  | Default | Description                    |
-| ------------------------ | ----- | ------- | ------------------------------ |
-| `height`                 | int   | None    | Image height in pixels         |
-| `width`                  | int   | None    | Image width in pixels          |
-| `size`                   | str   | None    | Image size (e.g., "1024x1024") |
-| `num_inference_steps`    | int   | 50      | Number of denoising steps      |
-| `true_cfg_scale`         | float | 4.0     | Qwen-Image CFG scale           |
-| `seed`                   | int   | None    | Random seed (reproducible)     |
-| `negative_prompt`        | str   | None    | Negative prompt                |
-| `num_outputs_per_prompt` | int   | 1       | Number of images to generate   |
+| Parameter                | Type  | Default | Description                        |
+| ------------------------ | ----- | ------- | ---------------------------------- |
+| `height`                 | int   | None    | Image height in pixels             |
+| `width`                  | int   | None    | Image width in pixels              |
+| `size`                   | str   | None    | Image size (e.g., "1024x1024")     |
+| `num_inference_steps`    | int   | 50      | Number of denoising steps          |
+| `true_cfg_scale`         | float | 4.0     | Qwen-Image CFG scale               |
+| `seed`                   | int   | None    | Random seed (reproducible)         |
+| `negative_prompt`        | str   | None    | Negative prompt                    |
+| `num_outputs_per_prompt` | int   | 1       | Number of images to generate       |
 | `--cfg-parallel-size`.   | int   | 1       | Number of GPUs for CFG parallelism |
 
 ## Response Format