LLaDA-o: An Effective and Length-Adaptive Omni Diffusion Model
Paper • 2603.01068 • Published • 22
How to use from
SGLangUse Docker images
docker run --gpus all \
--shm-size 32g \
-p 30000:30000 \
-v ~/.cache/huggingface:/root/.cache/huggingface \
--env "HF_TOKEN=<secret>" \
--ipc=host \
lmsysorg/sglang:latest \
python3 -m sglang.launch_server \
--model-path "GSAI-ML/LLaDA-V" \
--host 0.0.0.0 \
--port 30000# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "GSAI-ML/LLaDA-V",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'Quick Links
Update (March 2026): We are excited to introduce LLaDA-o, the latest model in the LLaDA series. As an effective and length-adaptive omni diffusion model for unified multimodal understanding and generation, LLaDA-o extends the LLaDA line to broader multimodal settings, supporting visual understanding, text-to-image generation, and instruction-based image editing. For more details, please check out the paper and code.
LLaDA-V
We introduce LLaDA-V, a competitive diffusion-based vision-language model that outperforms other diffusion MLLMs.
It was presented in the paper LLaDA-V: Large Language Diffusion Models with Visual Instruction Tuning.
Project Page: https://ml-gsai.github.io/LLaDA-V-demo/
- Downloads last month
- 4,462
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Install from pip and serve model
# Install SGLang from pip: pip install sglang# Start the SGLang server: python3 -m sglang.launch_server \ --model-path "GSAI-ML/LLaDA-V" \ --host 0.0.0.0 \ --port 30000# Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "GSAI-ML/LLaDA-V", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'