Instructions to use d3LLM/d3LLM_Dream_Coder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use d3LLM/d3LLM_Dream_Coder with Transformers:

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

pipe = pipeline("text-generation", model="d3LLM/d3LLM_Dream_Coder", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("d3LLM/d3LLM_Dream_Coder", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use d3LLM/d3LLM_Dream_Coder with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "d3LLM/d3LLM_Dream_Coder"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "d3LLM/d3LLM_Dream_Coder",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/d3LLM/d3LLM_Dream_Coder

SGLang

How to use d3LLM/d3LLM_Dream_Coder 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 "d3LLM/d3LLM_Dream_Coder" \
    --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": "d3LLM/d3LLM_Dream_Coder",
		"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 "d3LLM/d3LLM_Dream_Coder" \
        --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": "d3LLM/d3LLM_Dream_Coder",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use d3LLM/d3LLM_Dream_Coder with Docker Model Runner:
```
docker model run hf.co/d3LLM/d3LLM_Dream_Coder
```

d3LLM_Dream_Coder / README.md

d3LLM-model

Update README.md

84f9039 verified 2 months ago

preview code

Raw

History Blame Contribute Delete

2.37 kB

	---
	datasets:
	- d3LLM/Ling-Coder-dParallel-merged-512-120k
	base_model: Dream-org/Dream-Coder-v0-Instruct-7B
	pipeline_tag: text-generation
	library_name: transformers
	license: apache-2.0
	tags:
	- diffusion
	- fast-inference
	- d3llm
	---

	# d3LLM: Ultra-Fast Diffusion LLM using Pseudo-Trajectory Distillation 🚀

	d3LLM-Dream-Coder is an ultra-fast diffusion language model introduced in the paper [d3LLM: Ultra-Fast Diffusion LLM using Pseudo-Trajectory Distillation](https://huggingface.co/papers/2601.07568). It is built on [Dream-org/Dream-Coder-v0-Instruct-7B](https://huggingface.co/Dream-org/Dream-Coder-v0-Instruct-7B).

	## Model Description

	d3LLM (pseuDo-Distilled Diffusion Large Language Model) is a framework designed to strike a balance between accuracy and parallelism in diffusion LLMs. It achieves up to 10× speedup over vanilla diffusion models like LLaDA/Dream and 5× speedup over autoregressive (AR) models.

	The model utilizes two primary innovations:
	- Pseudo-Trajectory Distillation: A training method that teaches the model which tokens can be decoded confidently at early steps.
	- Entropy-Based Multi-Block Decoding: An inference strategy using a KV-cache refresh mechanism to maintain accuracy while maximizing parallelism.

	## Resources

	- Paper: [d3LLM: Ultra-Fast Diffusion LLM using Pseudo-Trajectory Distillation](https://huggingface.co/papers/2601.07568)
	- Repository: [https://github.com/hao-ai-lab/d3LLM](https://github.com/hao-ai-lab/d3LLM)
	- Blog: [https://hao-ai-lab.github.io/blogs/text-diffusion/](https://hao-ai-lab.github.io/blogs/text-diffusion/)
	- Demo: [https://d3llm-team.github.io/](https://d3llm-team.github.io/)

	## Usage

	For detailed usage instructions, evaluation scripts, and training code, please refer to the official GitHub repository. Since the model uses a custom architecture, ensure you have `transformers==4.49.0` installed and use `trust_remote_code=True` when loading the model.

	## Citation

	```bibtex
	@inproceedings{ICML'26:d3llm,
	title = {d3LLM: Ultra-Fast Diffusion LLM using Pseudo-Trajectory Distillation},
	author = {Yu-Yang Qian and Junda Su and Lanxiang Hu and Peiyuan Zhang and Zhijie Deng and Peng Zhao and Hao Zhang},
	booktitle = {Proceedings of the 43rd International Conference on Machine Learning (ICML)},
	pages = {to appear},
	year = {2026}
	}
	```