Instructions to use z-lab/Qwen3.5-397B-A17B-DFlash with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use z-lab/Qwen3.5-397B-A17B-DFlash with Transformers:

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

pipe = pipeline("text-generation", model="z-lab/Qwen3.5-397B-A17B-DFlash", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModel

tokenizer = AutoTokenizer.from_pretrained("z-lab/Qwen3.5-397B-A17B-DFlash", trust_remote_code=True)
model = AutoModel.from_pretrained("z-lab/Qwen3.5-397B-A17B-DFlash", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use z-lab/Qwen3.5-397B-A17B-DFlash with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "z-lab/Qwen3.5-397B-A17B-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/Qwen3.5-397B-A17B-DFlash",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/z-lab/Qwen3.5-397B-A17B-DFlash

SGLang

How to use z-lab/Qwen3.5-397B-A17B-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/Qwen3.5-397B-A17B-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/Qwen3.5-397B-A17B-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/Qwen3.5-397B-A17B-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/Qwen3.5-397B-A17B-DFlash",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use z-lab/Qwen3.5-397B-A17B-DFlash with Docker Model Runner:
```
docker model run hf.co/z-lab/Qwen3.5-397B-A17B-DFlash
```

Qwen3.5-397B-A17B-DFlash

Paper | Github | Blog

This is a joint release collaboration between Z-Lab, Modal, and SGLang. The draft model is mirrored across the following Hugging Face repositories:

This repository contains a DFlash draft model for Qwen/Qwen3.5-397B-A17B. It is not a standalone language model. It is intended to be paired with the target model in a speculative decoding server.

DFlash uses a lightweight block diffusion draft model to propose multiple tokens in parallel. The target model verifies those proposals, improving serving throughput while preserving the target model's output distribution.

Quick Start

Installation

DFlash serving requires a recent SGLang build. We recommend installing SGLang from a commit at or after ec36dde58083aca8f26c3740332498a11a06debf, which includes DFlash v2 overlap scheduling, DFlash sliding-window draft attention, and the required FlashInfer integration.

pip install -U \
  "git+https://github.com/sgl-project/sglang.git@ec36dde58083aca8f26c3740332498a11a06debf#subdirectory=python" \
  transformers hf_xet

For production serving, use a CUDA image with Blackwell support, such as lmsysorg/sglang:v0.5.13-cu130, and install the pinned SGLang commit inside the image.

Launch Server

This model should be used with an inference server that supports DFlash speculative decoding. An example SGLang deployment is:

export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1

python -m sglang.launch_server \
  --model-path Qwen/Qwen3.5-397B-A17B \
  --trust-remote-code \
  --speculative-algorithm DFLASH \
  --speculative-draft-model-path z-lab/Qwen3.5-397B-A17B-DFlash \
  --speculative-dflash-block-size 8 \
  --speculative-draft-attention-backend fa4 \
  --attention-backend trtllm_mha \
  --linear-attn-prefill-backend triton \
  --linear-attn-decode-backend flashinfer \
  --mamba-scheduler-strategy extra_buffer \
  --tp-size 8 \
  --max-running-requests 32 \
  --cuda-graph-max-bs-decode 32 \
  --cuda-graph-backend-prefill tc_piecewise \
  --enable-flashinfer-allreduce-fusion \
  --mem-fraction-static 0.8 \
  --host 0.0.0.0 \
  --port 30000

Block size 8 is the recommended default for higher-concurrency serving. Block size 16 gives longer accept lengths and the best concurrency-1 throughput in most workloads.

Benchmark Results

We benchmarked DFlash against the autoregressive baseline and Qwen3.5's built-in MTP draft path. DFlash reaches up to 4.31x speedup at concurrency 1 and 2.77x at concurrency 32. Across the benchmark suite, DFlash delivers higher throughput than MTP at every tested setting.

Setup

Runtime: SGLang on 8x NVIDIA B200 GPUs, tensor parallel size 8, bfloat16
Backends: trtllm_mha target attention, fa4 DFlash draft attention, flashinfer linear attention
Workloads: GSM8K, MATH500, HumanEval, MBPP, and MT-Bench with the Qwen chat template
Decoding: greedy, thinking enabled, max output length 4096 tokens
Measurement: 5 independent runs per configuration at concurrency 1 and 32 with continuous batching
Throughput: generated output tokens / wall-clock benchmark time, including prefill and scheduling
Accept length: completion_tokens / spec_verify_ct per generation turn, averaged across generation turns

For reproduction, the evaluation scripts, Modal runner, runtime patches, and raw benchmark outputs are included under benchmark/.

Throughput and Speedup

Each cell is output tok/s (speedup). Bold marks the fastest speculative configuration in each row.

Concurrency 1

Workload	Baseline	MTP steps=3	DFlash block=4	MTP steps=7	DFlash block=8	MTP steps=15	DFlash block=16
gsm8k	204.6 (1.00x)	484.5 (2.37x)	530.0 (2.59x)	536.7 (2.62x)	689.0 (3.37x)	439.2 (2.15x)	711.3 (3.48x)
math500	204.4 (1.00x)	505.2 (2.47x)	551.3 (2.70x)	589.4 (2.88x)	762.6 (3.73x)	499.8 (2.44x)	831.9 (4.07x)
humaneval	202.9 (1.00x)	483.0 (2.38x)	543.6 (2.68x)	557.9 (2.75x)	752.5 (3.71x)	480.5 (2.37x)	874.6 (4.31x)
mbpp	204.6 (1.00x)	487.4 (2.38x)	550.3 (2.69x)	543.7 (2.66x)	751.2 (3.67x)	445.6 (2.18x)	807.8 (3.95x)
mt-bench	202.6 (1.00x)	442.9 (2.19x)	473.6 (2.34x)	441.5 (2.18x)	545.9 (2.69x)	338.0 (1.67x)	515.3 (2.54x)

Concurrency 32

Workload	Baseline	MTP steps=3	DFlash block=4	MTP steps=7	DFlash block=8	MTP steps=15	DFlash block=16
gsm8k	2597.7 (1.00x)	4462.3 (1.72x)	5078.0 (1.95x)	4902.9 (1.89x)	6158.9 (2.37x)	4079.5 (1.57x)	5648.8 (2.17x)
math500	2615.5 (1.00x)	4838.6 (1.85x)	5318.6 (2.03x)	5601.6 (2.14x)	6910.5 (2.64x)	4855.0 (1.86x)	6857.8 (2.62x)
humaneval	2452.7 (1.00x)	3838.1 (1.56x)	5081.4 (2.07x)	4347.4 (1.77x)	6666.0 (2.72x)	3917.2 (1.60x)	6783.7 (2.77x)
mbpp	2582.3 (1.00x)	4129.8 (1.60x)	5265.7 (2.04x)	4461.0 (1.73x)	6681.4 (2.59x)	3783.7 (1.47x)	6344.1 (2.46x)
mt-bench	2537.3 (1.00x)	4024.6 (1.59x)	4425.3 (1.74x)	3991.7 (1.57x)	4763.2 (1.88x)	3100.3 (1.22x)	4016.0 (1.58x)

Accept Length

Mean accept length at concurrency 1. Bold marks the higher value in each matched MTP/DFlash pair.

Workload	MTP steps=3	DFlash block=4	MTP steps=7	DFlash block=8	MTP steps=15	DFlash block=16
gsm8k	3.578	3.548	5.612	5.738	7.006	7.696
math500	3.636	3.622	5.810	6.003	7.294	8.212
humaneval	3.643	3.697	5.893	6.292	7.541	9.344
mbpp	3.532	3.588	5.357	5.860	6.398	7.801
mt-bench	3.244	3.188	4.567	4.584	5.256	5.523

Citation

If you find DFlash useful, please cite the original paper:

@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}
}