Instructions to use fudan-generative-ai/D3D-1.7B-32B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use fudan-generative-ai/D3D-1.7B-32B with Transformers:

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

pipe = pipeline("text-generation", model="fudan-generative-ai/D3D-1.7B-32B", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("fudan-generative-ai/D3D-1.7B-32B", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("fudan-generative-ai/D3D-1.7B-32B", trust_remote_code=True, device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use fudan-generative-ai/D3D-1.7B-32B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "fudan-generative-ai/D3D-1.7B-32B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "fudan-generative-ai/D3D-1.7B-32B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/fudan-generative-ai/D3D-1.7B-32B

SGLang

How to use fudan-generative-ai/D3D-1.7B-32B 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 "fudan-generative-ai/D3D-1.7B-32B" \
    --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": "fudan-generative-ai/D3D-1.7B-32B",
		"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 "fudan-generative-ai/D3D-1.7B-32B" \
        --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": "fudan-generative-ai/D3D-1.7B-32B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use fudan-generative-ai/D3D-1.7B-32B with Docker Model Runner:
```
docker model run hf.co/fudan-generative-ai/D3D-1.7B-32B
```

D3D-1.7B-32B

1.7B draft for Qwen3-32B, released for D3D: Decoupled Diffusion Drafting for Asynchronous Speculative Decoding.

Code & quick start · All checkpoints

Model details

Property	Value
Role	Diffusion draft model; not the target verifier
Target verifier	Qwen/Qwen3-32B
Draft base architecture	Qwen3-1.7B
Transformer layers	28
Hidden size	2048
Vocabulary size	151936
Stored weight dtype	FP32 (original checkpoint tensors, no conversion)
Recommended inference dtype	BF16

Unpruned Qwen3-derived draft architecture.

The size in the model name describes the base draft family. The stored checkpoint can include untied embedding/output weights, and pruned variants have fewer layers; the exact tensor parameter count is reported in release_metadata.json.

Quick start

Install the dependencies in the D3D repository, then run from its root:

export TARGET_MODEL=Qwen/Qwen3-32B
export DRAFT_MODEL=fudan-generative-ai/D3D-1.7B-32B
bash scripts/quickstart_single.sh

For concurrent requests:

CONCURRENCY=4 bash scripts/quickstart_concurrent.sh

The target runs on GPU 0 and the draft on GPU 1. D3D uses its checked-in D3D compatibility classes and does not execute Hub-hosted Python during inference. Use the pinned D3D environment (PyTorch 2.8.0 / Transformers 4.57.3).