tencent/Qwen3-8B-DSpine-b16
tencent/Qwen3-8B-DSpine-b16
Qwen3-8B-DSpine-b16 released by Qwen, employing speculative decoding technology with parallel drafting and deep conditional injection, achieving an average acceptance length score of 10.55 on Qwen3-8B. The model supports a context length of 8192 tokens, uses bfloat16 data type and fa3 attention backend, installation requires git clone and pip install, and runs via sglang serve.
Draft in Parallel, Condition Through Depth: Adjacent Causal Injection for Speculative Decoding
DSpine is a parallel drafter for speculative decoding. At every draft layer, each position receives the predicted feature of its predecessor, so the causal chain unfolds over network depth while all positions are still drafted in parallel.
News
- [2026-10] Inference code released.
- [2026-09] Paper released on arXiv.
Results
Acceptance length on Qwen3-8B. DSpine, DSpark and DFlash2 are all retrained on Open-PerfectBlend with the same configuration.
| Temp. | Method | GSM8K | MATH-500 | HumanEval | MBPP | LCB | MT-Bench | Arena-Hard | Avg. |
|---|---|---|---|---|---|---|---|---|---|
| T = 0 | DFlash† | 6.32 | 7.99 | 6.56 | 6.29 | 6.11 | 4.26 | 3.91 | 5.92 |
| Domino† | 9.68 | 9.40 | 7.23 | 6.89 | 6.40 | 5.12 | 4.65 | 7.05 | |
| DSpark | 10.00 | 9.88 | 7.78 | 7.35 | 6.81 | 5.39 | 4.87 | 7.44 | |
| DFlash2 | 10.06 | 10.04 | 7.99 | 7.33 | 6.96 | 5.40 | 5.06 | 7.55 | |
| DSpine | 10.55 | 10.30 | 8.27 | 7.66 | 7.25 | 5.63 | 5.13 | 7.83 | |
| T = 1 | DFlash† | 5.75 | 6.51 | 5.52 | 5.23 | 4.53 | 3.77 | 3.25 | 4.94 |
| Domino† | 8.01 | 7.13 | 5.89 | 5.56 | 4.59 | 4.36 | 3.61 | 5.59 | |
| DSpark | 9.33 | 8.64 | 6.91 | 6.66 | 5.78 | 4.99 | 4.25 | 6.65 | |
| DFlash2 | 9.07 | 8.42 | 6.99 | 6.43 | 5.67 | 4.90 | 4.25 | 6.53 | |
| DSpine | 9.83 | 8.99 | 7.39 | 6.97 | 6.11 | 5.09 | 4.49 | 6.98 |
† Official checkpoints: z-lab/Qwen3-8B-DFlash-b16 and Huang2020/Qwen3-8B-Domino-b16.
Installation
git clone https://github.com/tencent/dspine.git
cd dspine
pip install -e .
Usage
The server settings below are the ones behind the acceptance lengths and throughput reported in the paper.
sglang serve \
--model-path Qwen/Qwen3-8B \
--speculative-algorithm DSPINE \
--speculative-draft-model-path <dspine-model-path> \
--speculative-num-draft-tokens 16 \
--dtype bfloat16 \
--attention-backend fa3 \
--page-size 1 \
--mem-fraction-static 0.65 \
--context-length 8192 \
--max-running-requests 64 \
--cuda-graph-bs-decode 1 2 4 8 16 32 64 \
--trust-remote-code
Roadmap
☐ Training code for DSpine
☐ DSpine for Qwen3.8-27B
Acknowledgements
We thank DFlash, SpecForge, SGLang and FlashInfer for their open-source work.
Citation
@article{zhang2026dspine,
title = {Draft in Parallel, Condition Through Depth: Adjacent Causal Injection for Speculative Decoding},
author = {Zhang, Haohui and Chen, Keyu and Sun, Haocheng and Gu, Weibo and Qiao, Ruizhi and Sun, Xing and Jiang, Bo},
journal = {arXiv preprint arXiv:2609.36173},
year = {2026}
}
License
Source: Tencent Hunyuan · Hugging Face new models · huggingface.co