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, dtype="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-model commited on May 25

Commit

84f9039

verified ·

1 Parent(s): 8796070

Update README.md

Browse files

Files changed (1) hide show

README.md +6 -6

README.md CHANGED Viewed

@@ -37,11 +37,11 @@ For detailed usage instructions, evaluation scripts, and training code, please r
 ## Citation
 ```bibtex
-@article{arxiv'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},
-  journal = {ArXiv preprint},
-  volume  = {arXiv:2601.07568},
-  year    = {2026}
 }
 ```

 ## 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}
 }
 ```