Instructions to use z-lab/gemma-4-31B-it-DFlash with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use z-lab/gemma-4-31B-it-DFlash with Transformers:

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

pipe = pipeline("text-generation", model="z-lab/gemma-4-31B-it-DFlash")

# Load model directly
from transformers import AutoTokenizer, AutoModel

tokenizer = AutoTokenizer.from_pretrained("z-lab/gemma-4-31B-it-DFlash")
model = AutoModel.from_pretrained("z-lab/gemma-4-31B-it-DFlash")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use z-lab/gemma-4-31B-it-DFlash with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "z-lab/gemma-4-31B-it-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/gemma-4-31B-it-DFlash",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/z-lab/gemma-4-31B-it-DFlash

SGLang

How to use z-lab/gemma-4-31B-it-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/gemma-4-31B-it-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/gemma-4-31B-it-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/gemma-4-31B-it-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/gemma-4-31B-it-DFlash",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use z-lab/gemma-4-31B-it-DFlash with Docker Model Runner:
```
docker model run hf.co/z-lab/gemma-4-31B-it-DFlash
```

gemma-4-31B-it-DFlash / README.md

jianchen0311

Update README.md

9f539d7 verified 11 days ago

preview code

raw

history blame contribute delete

4.42 kB

	---
	license: apache-2.0
	library_name: transformers
	pipeline_tag: text-generation
	tags:
	- dflash
	- speculative-decoding
	- block-diffusion
	- draft-model
	- efficiency
	- qwen
	- gemma
	- diffusion-language-model
	---

	# gemma-4-31B-it-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 [google/gemma-4-31B-it](https://huggingface.co/google/gemma-4-31B-it).

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

	## Quick Start

	### Installation

	vLLM: until Gemma4 DFlash support is merged, install vLLM from [PR #41703](https://github.com/vllm-project/vllm/pull/41703):

	```bash
	uv pip install -U --torch-backend=auto \
	"vllm @ git+https://github.com/vllm-project/vllm.git@refs/pull/41703/head"
	```

	SGLang:

	```bash
	uv pip install "git+https://github.com/sgl-project/sglang.git@refs/pull/23000/head#subdirectory=python"
	```

	### Launch Server

	vLLM:

	```bash
	vllm serve google/gemma-4-31B-it \
	--speculative-config '{"method": "dflash", "model": "z-lab/gemma-4-31B-it-DFlash", "num_speculative_tokens": 15, "attention_backend": "flash_attn"}' \
	--attention-backend triton_attn \
	--max-num-batched-tokens 32768 \
	--trust-remote-code
	```

	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 google/gemma-4-31B-it \
	--speculative-algorithm DFLASH \
	--speculative-draft-model-path z-lab/gemma-4-31B-it-DFlash \
	--speculative-num-draft-tokens 16 \
	--tp-size 1 \
	--attention-backend triton \
	--speculative-draft-attention-backend fa4 \
	--trust-remote-code
	```

	### Usage

	For vLLM, use port `8000`. For SGLang, use port `30000`.

	```python
	from openai import OpenAI

	client = OpenAI(base_url="http://localhost:8000/v1", api_key="EMPTY")

	response = client.chat.completions.create(
	model="google/gemma-4-31B-it",
	messages=[{"role": "user", "content": "Write a quicksort in Python."}],
	max_tokens=4096,
	temperature=0.0,
	extra_body={"chat_template_kwargs": {"enable_thinking": True}},
	)
	print(response.choices[0].message.content)
	```

	## Benchmark Results

	Setup: Single NVIDIA B300 GPU per server/run, vLLM, thinking enabled, max output length 4096, greedy decoding.

	### Throughput and Speedup

	DFlash achieves up to 5.8x speedup at concurrency 1.

	_Generated tokens/sec (speedup vs. autoregressive baseline)_

	Block Size = 16

	\| Task \| Concurrency \| AR \| DFlash \|
	\|---\|---:\|---:\|---:\|
	\| Math500 \| 1 \| 77 \| 447 (5.8x) \|
	\| \| 8 \| 511 \| 2650 (5.2x) \|
	\| \| 32 \| 1308 \| 4962 (3.8x) \|
	\| GSM8K \| 1 \| 78 \| 408 (5.3x) \|
	\| \| 8 \| 520 \| 2321 (4.5x) \|
	\| \| 32 \| 1382 \| 4447 (3.2x) \|
	\| HumanEval \| 1 \| 76 \| 420 (5.6x) \|
	\| \| 8 \| 494 \| 2389 (4.8x) \|
	\| \| 32 \| 1145 \| 4139 (3.6x) \|
	\| MBPP \| 1 \| 79 \| 343 (4.4x) \|
	\| \| 8 \| 535 \| 2036 (3.8x) \|
	\| \| 32 \| 1389 \| 3636 (2.6x) \|
	\| MT-Bench \| 1 \| 79 \| 236 (3.0x) \|
	\| \| 8 \| 503 \| 1334 (2.7x) \|
	\| \| 32 \| 1177 \| 2257 (1.9x) \|

	### Acceptance Length

	\| Task \| c1 \| c8 \| c32 \|
	\|---\|---:\|---:\|---:\|
	\| Math500 \| 8.59 \| 8.59 \| 8.62 \|
	\| GSM8K \| 7.53 \| 7.50 \| 7.52 \|
	\| HumanEval \| 8.00 \| 7.89 \| 7.96 \|
	\| MBPP \| 6.13 \| 6.13 \| 6.14 \|
	\| MT-Bench \| 4.23 \| 4.19 \| 4.19 \|

	## 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}
	}
	```