Instructions to use ZhenbangDu/R2-dLLM-LLaDA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ZhenbangDu/R2-dLLM-LLaDA with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="ZhenbangDu/R2-dLLM-LLaDA", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("ZhenbangDu/R2-dLLM-LLaDA", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ZhenbangDu/R2-dLLM-LLaDA with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ZhenbangDu/R2-dLLM-LLaDA"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ZhenbangDu/R2-dLLM-LLaDA",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ZhenbangDu/R2-dLLM-LLaDA

SGLang

How to use ZhenbangDu/R2-dLLM-LLaDA with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "ZhenbangDu/R2-dLLM-LLaDA" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ZhenbangDu/R2-dLLM-LLaDA",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use 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 "ZhenbangDu/R2-dLLM-LLaDA" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ZhenbangDu/R2-dLLM-LLaDA",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ZhenbangDu/R2-dLLM-LLaDA with Docker Model Runner:
```
docker model run hf.co/ZhenbangDu/R2-dLLM-LLaDA
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

$R^2$-dLLM-LLaDA

$R^2$-dLLM is a unified framework for reducing decoding redundancy in Diffusion Large Language Models (dLLMs) from both inference and training perspectives. This specific checkpoint is a redundancy-aware supervised fine-tuned version of LLaDA-Instruct-8B.

Paper: $R^2$-dLLM: Accelerating Diffusion Large Language Models via Spatio-Temporal Redundancy Reduction
Code: Official GitHub Repository

Description

Diffusion Large Language Models (dLLMs) enable parallel token prediction but often suffer from high inference latency due to decoding redundancy. $R^2$-dLLM addresses this by:

Inference-time rules: Aggregating local confidence and finalized predictions to avoid redundant decoding steps.
Redundancy-aware SFT: Aligning the model with efficient decoding trajectories during training.

Experiments demonstrate that $R^2$-dLLM consistently reduces the number of decoding steps by up to 88% compared to existing decoding strategies, while maintaining competitive generation quality across different models and tasks.

Citation

@article{du2026r,
  title={$R^{2}$-dLLM: Accelerating Diffusion Large Language Models via Spatio-Temporal Redundancy Reduction},
  author={Du, Zhenbang and Xia, Kejing and Zhong, Xinrui and Fu, Yonggan and Oswald, Nicolai and Ji, Binfei and Khailany, Brucek and Molchanov, Pavlo and Lin, Yingyan},
  journal={arXiv preprint arXiv:2604.18995},
  year={2026}
}