anodyine/vllm-omni
1
0 Fork 0
Code Issues 4 Pull Requests 2 Actions Packages Projects Releases Wiki Activity

update docs (#536)

Browse Source 
Signed-off-by: hsliu <liuhongsheng4@huawei.com>
This commit is contained in:
Hongsheng Liu authored and GitHub committed 2025-12-30 21:55:32 +08:00
1 parent 1ae0c64fe0
commit 51c0303945
11 files changed
+25 -74
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

docs/contributing/README.md
+6 -13
View File
@@ -13,25 +13,18 @@ vLLM-Omni uses `uv` as the environment manager, to create and manage Python envi
uv venv --python 3.12 --seed
source .venv/bin/activate
```
### Development Environment for vLLM
vLLM-Omni is built on top of the stable release 0.12.0 of vLLM. You may install `vllm==0.12.0` directly or install the library from source if you need to check, modify or debug with source code of vLLM.
### Development Environment for vLLM and vLLM-Omni
The release 0.12.0 of vLLM is based on PyTorch 2.9.0 which requires CUDA 12.9 environment.
### Development Environment for vLLM-Omni
Install vLLM-Omni from source with development dependencies:
```bash
git clone https://github.com/vllm-project/vllm-omni.git
cd vllm-omni
uv pip install -e ".[dev]"
```
vLLM-Omni is quickly evolving, please see the [installation guide](../getting_started/installation/README.md) for details. It's recommended to build from source to provide the latest development environment.
!!! tip
vLLM-Omni is compatible with Python versions 3.10 to 3.12. However, we recommend developing with Python 3.12 to minimize the chance of your local environment clashing with our CI environment.
### Adding a new model to vLLM-Omni
Please check [model implementation](model/README.md) for how to add diffusion and omni-modality models to vLLM-Omni.
### Linting
vLLM-Omni uses `pre-commit` to lint and format the codebase. See [pre-commit documentation](https://pre-commit.com/#usage) if `pre-commit` is new to you. Setting up `pre-commit` is as easy as:
docs/contributing/model/README.md
+1 -1
View File
@@ -26,4 +26,4 @@ The guide covers:
## Quick Start
For a quick reference, see the [Adding a New Omni Model Guide](adding_multi_stage_model.md) and [Adding a New Diffusion Model Guide](adding_diffusion_model.md).
For a quick reference, see the [Adding a New Multi-Stage Model Guide](adding_multi_stage_model.md) and [Adding a New Diffusion Model Guide](adding_diffusion_model.md).
docs/contributing/model/adding_diffusion_model.md
+1 -1
View File
@@ -1,4 +1,4 @@
# Adding a New Diffusion Model to vLLM-Omni
# Adding a Diffusion Model
This guide walks through the process of adding a new Diffusion model to vLLM-Omni, using Qwen/Qwen-Image-Edit as a comprehensive example.
# Table of Contents
docs/contributing/model/adding_multi_stage_model.md
+2 -2
View File
@@ -1,6 +1,6 @@
# Adding a New Multi-Stage Model to vLLM-Omni
# Adding a Multi-Stage Model
This guide walks through the process of adding a new model to vLLM-Omni, using **Qwen3-Omni** as a comprehensive example. Qwen3-Omni is a multi-stage omni-modality model that demonstrates the full capabilities of vLLM-Omni's architecture.
This guide walks through the process of adding a new multi-stage model to vLLM-Omni, using **Qwen3-Omni** as a comprehensive example. Qwen3-Omni is a multi-stage omni-modality model that demonstrates the full capabilities of vLLM-Omni's architecture.
## Table of Contents
docs/contributing/profiling.md
+1 -1
View File
@@ -1,3 +1,3 @@
# Profiling vLLM-Omni (update soon)
# Profiling vLLM-Omni
Profiling is only intended for vLLM-Omni developers and maintainers to understand the proportion of time spent in different parts of the codebase. **vLLM-Omni end-users should never turn on profiling** as it will significantly slow down the inference.
docs/getting_started/installation/gpu/cuda.inc.md
+3 -1
View File
@@ -42,8 +42,10 @@ If you do not need to modify source code of vLLM, you can directly install the s
uv pip install vllm==0.12.0 --torch-backend=auto
```
The release 0.12.0 of vLLM is based on PyTorch 2.9.0 which requires CUDA 12.9 environment.
#### Installation of vLLM-Omni
Install additional requirements for vLLM-Omni
Since vllm-omni is rapidly evolving, it's recommended to install it from source
```bash
git clone https://github.com/vllm-project/vllm-omni.git
cd vllm-omni
docs/getting_started/quickstart.md
+1 -1
View File
@@ -23,7 +23,7 @@ cd vllm-omni
uv pip install -e .
```
For additional details—including alternative installation methods, installation on NPU and other platforms — please see the installation guide in [installation](installation/README.md)
For additional installation methods — please see the [installation guide](installation/README.md).
## Offline Inference
docs/user_guide/examples/offline_inference/qwen2_5_omni.md
-7
View File
@@ -70,13 +70,6 @@ If media file paths are not provided, the script will use default assets. Suppor
- `use_audio_in_video`: Extract audio from video
- `text`: Text-only query
### FAQ
If you encounter error about backend of librosa, try to install ffmpeg with command below.
```
sudo apt update
sudo apt install ffmpeg
```
## Example materials
docs/user_guide/examples/offline_inference/qwen3_omni.md
-7
View File
@@ -57,13 +57,6 @@ If media file paths are not provided, the script will use default assets. Suppor
- `use_audio`: Audio input
- `text`: Text-only query
### FAQ
If you encounter error about backend of librosa, try to install ffmpeg with command below.
```
sudo apt update
sudo apt install ffmpeg
```
## Example materials
docs/user_guide/examples/online_serving/qwen2_5_omni.md
+5 -20
View File
@@ -35,26 +35,11 @@ python openai_chat_completion_client_for_multimodal_generation.py --query-type m
The Python client supports the following command-line arguments:
- `--query-type` (or `-q`): Query type (default: `mixed_modalities`)
- Options: `mixed_modalities`, `use_audio_in_video`, `multi_audios`, `text`
- `--video-path` (or `-v`): Path to local video file or URL
- If not provided and query-type uses video, uses default video URL
- Supports local file paths (automatically encoded to base64) or HTTP/HTTPS URLs
- Example: `--video-path /path/to/video.mp4` or `--video-path https://example.com/video.mp4`
- `--image-path` (or `-i`): Path to local image file or URL
- If not provided and query-type uses image, uses default image URL
- Supports local file paths (automatically encoded to base64) or HTTP/HTTPS URLs
- Supports common image formats: JPEG, PNG, GIF, WebP
- Example: `--image-path /path/to/image.jpg` or `--image-path https://example.com/image.png`
- `--audio-path` (or `-a`): Path to local audio file or URL
- If not provided and query-type uses audio, uses default audio URL
- Supports local file paths (automatically encoded to base64) or HTTP/HTTPS URLs
- Supports common audio formats: MP3, WAV, OGG, FLAC, M4A
- Example: `--audio-path /path/to/audio.wav` or `--audio-path https://example.com/audio.mp3`
- `--prompt` (or `-p`): Custom text prompt/question
- If not provided, uses default prompt for the selected query type
- Example: `--prompt "What are the main activities shown in this video?"`
- `--query-type` (or `-q`): Query type (default: `mixed_modalities`). Options: `mixed_modalities`, `use_audio_in_video`, `multi_audios`, `text`
- `--video-path` (or `-v`): Path to local video file or URL. If not provided and query-type uses video, uses default video URL. Supports local file paths (automatically encoded to base64) or HTTP/HTTPS URLs. Example: `--video-path /path/to/video.mp4` or `--video-path https://example.com/video.mp4`
- `--image-path` (or `-i`): Path to local image file or URL. If not provided and query-type uses image, uses default image URL. Supports local file paths (automatically encoded to base64) or HTTP/HTTPS URLs and common image formats: JPEG, PNG, GIF. Example: `--image-path /path/to/image.jpg` or `--image-path https://example.com/image.png`
- `--audio-path` (or `-a`): Path to local audio file or URL. If not provided and query-type uses audio, uses default audio URL. Supports local file paths (automatically encoded to base64) or HTTP/HTTPS URLs and common audio formats: MP3, WAV, OGG, FLAC, M4A. Example: `--audio-path /path/to/audio.wav` or `--audio-path https://example.com/audio.mp3`
- `--prompt` (or `-p`): Custom text prompt/question. If not provided, uses default prompt for the selected query type. Example: `--prompt "What are the main activities shown in this video?"`
For example, to use mixed modalities with all local files:
docs/user_guide/examples/online_serving/qwen3_omni.md
+5 -20
View File
@@ -35,27 +35,12 @@ python openai_chat_completion_client_for_multimodal_generation.py --query-type u
The Python client supports the following command-line arguments:
- `--query-type` (or `-q`): Query type (default: `use_video`)
- Options: `text`, `use_audio`, `use_image`, `use_video`
- `--query-type` (or `-q`): Query type (default: `use_video`). Options: `text`, `use_audio`, `use_image`, `use_video`
- `--model` (or `-m`): Model name/path (default: `Qwen/Qwen3-Omni-30B-A3B-Instruct`)
- `--video-path` (or `-v`): Path to local video file or URL
- If not provided and query-type is `use_video`, uses default video URL
- Supports local file paths (automatically encoded to base64) or HTTP/HTTPS URLs
- Example: `--video-path /path/to/video.mp4` or `--video-path https://example.com/video.mp4`
- `--image-path` (or `-i`): Path to local image file or URL
- If not provided and query-type is `use_image`, uses default image URL
- Supports local file paths (automatically encoded to base64) or HTTP/HTTPS URLs
- Supports common image formats: JPEG, PNG, GIF, WebP
- Example: `--image-path /path/to/image.jpg` or `--image-path https://example.com/image.png`
- `--audio-path` (or `-a`): Path to local audio file or URL
- If not provided and query-type is `use_audio`, uses default audio URL
- Supports local file paths (automatically encoded to base64) or HTTP/HTTPS URLs
- Supports common audio formats: MP3, WAV, OGG, FLAC, M4A
- Example: `--audio-path /path/to/audio.wav` or `--audio-path https://example.com/audio.mp3`
- `--prompt` (or `-p`): Custom text prompt/question
- If not provided, uses default prompt for the selected query type
- Example: `--prompt "What are the main activities shown in this video?"`
- `--video-path` (or `-v`): Path to local video file or URL. If not provided and query-type is `use_video`, uses default video URL. Supports local file paths (automatically encoded to base64) or HTTP/HTTPS URLs. Example: `--video-path /path/to/video.mp4` or `--video-path https://example.com/video.mp4`
- `--image-path` (or `-i`): Path to local image file or URL. If not provided and query-type is `use_image`, uses default image URL. Supports local file paths (automatically encoded to base64) or HTTP/HTTPS URLs and common image formats: JPEG, PNG, GIF. Example: `--image-path /path/to/image.jpg` or `--image-path https://example.com/image.png`.
- `--audio-path` (or `-a`): Path to local audio file or URL. If not provided and query-type is `use_audio`, uses default audio URL. Supports local file paths (automatically encoded to base64) or HTTP/HTTPS URLs and common audio formats: MP3, WAV, OGG, FLAC, M4A. Example: `--audio-path /path/to/audio.wav` or `--audio-path https://example.com/audio.mp3`
- `--prompt` (or `-p`): Custom text prompt/question. If not provided, uses default prompt for the selected query type. Example: `--prompt "What are the main activities shown in this video?"`
For example, to use a local video file with custom prompt: