Instructions to use z-lab/Qwen3-Coder-Next-DFlash with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use z-lab/Qwen3-Coder-Next-DFlash with Transformers:

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

pipe = pipeline("text-generation", model="z-lab/Qwen3-Coder-Next-DFlash", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModel

tokenizer = AutoTokenizer.from_pretrained("z-lab/Qwen3-Coder-Next-DFlash", trust_remote_code=True)
model = AutoModel.from_pretrained("z-lab/Qwen3-Coder-Next-DFlash", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use z-lab/Qwen3-Coder-Next-DFlash with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "z-lab/Qwen3-Coder-Next-DFlash"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "z-lab/Qwen3-Coder-Next-DFlash",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/z-lab/Qwen3-Coder-Next-DFlash

SGLang

How to use z-lab/Qwen3-Coder-Next-DFlash 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 "z-lab/Qwen3-Coder-Next-DFlash" \
    --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": "z-lab/Qwen3-Coder-Next-DFlash",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "z-lab/Qwen3-Coder-Next-DFlash" \
        --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": "z-lab/Qwen3-Coder-Next-DFlash",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use z-lab/Qwen3-Coder-Next-DFlash with Docker Model Runner:
```
docker model run hf.co/z-lab/Qwen3-Coder-Next-DFlash
```

Qwen3-Coder-Next-DFlash / README.md

jianchen0311

Update README.md

6d741db verified 4 months ago

preview code

Raw

History Blame

3.36 kB

	---
	license: mit
	library_name: transformers
	pipeline_tag: text-generation
	tags:
	- dflash
	- speculative-decoding
	- block-diffusion
	- draft-model
	- efficiency
	- qwen
	- diffusion-language-model
	---

	# Qwen3-Coder-Next-DFlash

	[Paper](https://arxiv.org/abs/2602.06036) \| [GitHub](https://github.com/z-lab/dflash) \| [Blog](https://z-lab.ai/projects/dflash/)

	DFlash is a speculative decoding method that uses a lightweight block diffusion model to draft multiple tokens in parallel. This is the drafter model, which must be paired with [Qwen/Qwen3-Coder-Next](https://huggingface.co/Qwen/Qwen3-Coder-Next).

	<div align="center">
	<img src="assets/dflash_system.png" alt="DFlash Architecture" width="85%">
	</div>

	## Quick Start

	### Installation

	vLLM:
	```bash
	uv pip install vllm
	uv pip install -U vllm --torch-backend=auto --extra-index-url https://wheels.vllm.ai/nightly
	```

	SGLang:
	```bash
	uv pip install "git+https://github.com/sgl-project/sglang.git@refs/pull/20547/head#subdirectory=python"
	```

	### Launch Server

	vLLM:
	```bash
	vllm serve Qwen/Qwen3-Coder-Next \
	--speculative-config '{"method": "dflash", "model": "z-lab/Qwen3-Coder-Next-DFlash", "num_speculative_tokens": 15}' \
	--attention-backend flash_attn \
	--max-num-batched-tokens 32768
	```

	SGLang:
	```bash
	# Optional: enable schedule overlapping (experimental, may not be stable)
	# export SGLANG_ENABLE_SPEC_V2=1
	# export SGLANG_ENABLE_DFLASH_SPEC_V2=1
	# export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1

	python -m sglang.launch_server \
	--model-path Qwen/Qwen3-Coder-Next \
	--speculative-algorithm DFLASH \
	--speculative-draft-model-path z-lab/Qwen3-Coder-Next-DFlash \
	--speculative-num-draft-tokens 16 \
	--tp-size 1 \
	--attention-backend fa3 \
	--mem-fraction-static 0.75 \
	--mamba-scheduler-strategy extra_buffer \
	--trust-remote-code
	```
	> Tip: For long-context or agentic workloads, add `--speculative-dflash-draft-window-size WINDOW_SIZE` to enable sliding-window attention for the drafter.

	### Usage

	```python
	from openai import OpenAI

	client = OpenAI(base_url="http://localhost:30000/v1", api_key="EMPTY")

	response = client.chat.completions.create(
	model="Qwen/Qwen3-Coder-Next",
	messages=[{"role": "user", "content": "Write a quicksort in Python."}],
	max_tokens=4096,
	temperature=0.0
	)
	print(response.choices[0].message.content)
	```

	## Acceptance Length

	- Max new tokens: 4096
	- Block size: 16
	\| Dataset \| Accept Length \|
	\|-----------\|---------------\|
	\| HumanEval \| 7.25 \|
	\| MBPP \| 5.50 \|
	\| LiveCodeBench \| 5.50 \|

	## Acknowledgements

	Special thanks to [David Wang](https://davidwa.ng/) for his outstanding engineering support on this project. We are also grateful to [Modal](https://modal.com/), [InnoMatrix](https://innomatrix.ai), and [Yotta Labs](https://www.yottalabs.ai/) for providing the compute resources used to train this draft model.

	## Citation

	If you find DFlash useful, please cite our work. To share feedback on DFlash or request new model support, please fill out this form: [DFlash Feedback](https://forms.gle/4YNwfqb4nJdqn6hq9).

	```bibtex
	@article{chen2026dflash,
	title = {{DFlash: Block Diffusion for Flash Speculative Decoding}},
	author = {Chen, Jian and Liang, Yesheng and Liu, Zhijian},
	journal = {arXiv preprint arXiv:2602.06036},
	year = {2026}
	}
	```