---
pipeline_tag: text-generation
library_name: transformers
base_model:
  - zai-org/GLM-5.3-Flash
license: mit
license_link: LICENSE
inference: false
tags:
  - dflash
  - speculative-decoding
  - speculative-decoding-draft
  - block-diffusion
  - draft-model
  - glm
  - glm-5.3
  - sglang
---

# GLM-5.3-Flash-DFlash

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

This repository contains a DFlash draft model for [`zai-org/GLM-5.3-Flash`](https://huggingface.co/zai-org/GLM-5.3-Flash). 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

GLM-5.3-Flash needs the DFlash capture hooks in the `glm5_next` model, available on SGLang main. An example deployment is:

```bash
python -m sglang.launch_server \
  --model-path zai-org/GLM-5.3-Flash \
  --tp-size 4 \
  --trust-remote-code \
  --speculative-algorithm DFLASH \
  --speculative-draft-model-path modal-labs/GLM-5.3-Flash-DFlash \
  --speculative-dflash-block-size 8 \
  --speculative-draft-model-quantization unquant \
  --speculative-draft-attention-backend trtllm_mha \
  --speculative-draft-kv-cache-dtype fp8_e4m3 \
  --host 0.0.0.0 \
  --port 30000
```

Keep the draft model unquantized. Quantizing it lowers the accept length.

## License

Distributed under the [MIT License](LICENSE), inherited from the target model.

## Citation

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

```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}
}
```