chenchenghao/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity

update multimodal_gen readme (#12825)

Browse Source 
Co-authored-by: Xinyuan Tong <115166877+JustinTong0323@users.noreply.github.com>
This commit is contained in:
Mick
2025-11-08 01:04:44 +08:00
committed by GitHub
parent 0fe9c1f70b
commit e316bcacb1
2 changed files with 13 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files

27
python/sglang/multimodal_gen/README.md
View File

@@ -1,25 +1,18 @@
<div align="center">
<img src=assets/logos/logo.svg width="30%"/>
<div align="center" style="display:block; margin:auto;">
<img src=https://github.com/lm-sys/lm-sys.github.io/releases/download/test/sgl-diffusion-logo.png width="80%"/>
</div>
**sgl-diffusion is an inference framework for accelerated image/video generation.**
sgl-diffusion features an end-to-end unified pipeline for accelerating diffusion models. It is designed to be modular and extensible, allowing users to easily add new optimizations and techniques.
SGLang-Diffusion features an end-to-end unified pipeline for accelerating diffusion models. It is designed to be modular and extensible, allowing users to easily add new models and optimizations.
## Key Features
sgl-diffusion has the following features:
- State-of-the-art performance optimizations for inference
- [Video Sparse Attention](https://arxiv.org/pdf/2505.13389)
- [Sliding Tile Attention](https://arxiv.org/pdf/2502.04507)
- [TeaCache](https://arxiv.org/pdf/2411.19108)
- [Sage Attention](https://arxiv.org/abs/2410.02367)
- USP
- CFG Parallel
- Diverse hardware and OS support
- Supported hardware: H100, H200, A100, B200, 4090
- Supported OS: Linux, Windows, MacOS
SGLang Diffusion has the following features:
- Broad model support: Wan series, FastWan series, Hunyuan, Qwen-Image, Qwen-Image-Edit, Flux
- Fast inference speed: enpowered by highly optimized kernel from sgl-kernel and efficient scheduler loop
- Ease of use: OpenAI-compatible api, CLI, and python sdk support
- Diverse hardware support: H100, H200, A100, B200, 4090
## Getting Started
@@ -27,7 +20,7 @@ sgl-diffusion has the following features:
uv pip install 'sglang[diffusion]' --prerelease=allow
```
For more information, check the [docs](https://github.com/sgl-project/sglang/tree/main/python/sglang/multimodal_gen/docs/install.md).
For more installation methods (e.g. pypi, uv, docker), check the [docs](https://github.com/sgl-project/sglang/tree/main/python/sglang/multimodal_gen/docs/install.md).
## Inference
@@ -68,7 +61,7 @@ sglang generate --model-path Wan-AI/Wan2.1-T2V-1.3B-Diffusers \
--save-output
```
For more information, check the [docs](https://github.com/sgl-project/sglang/tree/main/python/sglang/multimodal_gen/docs/cli.md).
For more usage examples (e.g. OpenAI compatible API, server mode), check the [docs](https://github.com/sgl-project/sglang/tree/main/python/sglang/multimodal_gen/docs/cli.md).
## Contributing

6
python/sglang/multimodal_gen/docs/install.md
View File

@@ -11,7 +11,7 @@ It is recommended to use uv for a faster installation:
```bash
pip install --upgrade pip
pip install uv
uv pip install 'sglang[diffusion]' --prerelease=allow
uv pip install "sglang[diffusion]" --prerelease=allow
```
## Method 2: From source
@@ -23,10 +23,10 @@ cd sglang
# Install the Python packages
pip install --upgrade pip
pip install -e "python/.[diffusion]"
pip install -e "python[diffusion]"
# With uv
uv pip install --prerelease=allow -e "python/.[diffusion]"
uv pip install -e "python[diffusion]" --prerelease=allow
```
## Method 3: Using Docker