Anbeeld / Kimi-K2.5-DFlash-GGUF

Kimi K2.5 DFlash GGUF

GGUF quantizations of z-lab DFlash draft model for Kimi K2.5 .

Use with BeeLlama.cpp , a llama.cpp fork with advanced quantization features.

Kimi-K2.5-DFlash

Paper | GitHub | Blog

DFlash is a novel speculative decoding method that utilizes a lightweight block diffusion model for drafting. It enables efficient, high-quality parallel drafting that pushes the limits of inference speed.

This model is the drafter component. It must be used in conjunction with the target model moonshotai/Kimi-K2.5 .

Quick Start

Installation

SGLang:

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

vLLM:

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

Please refer to PR39930 to see how to use DFlash with Kimi-K2.5 on vLLM.

Launch Server

SGLang:

# 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 moonshotai/Kimi-K2.5 \
    --speculative-algorithm DFLASH \
    --speculative-draft-model-path z-lab/Kimi-K2.5-DFlash \
    --speculative-num-draft-tokens 8 \
    --tp-size 8 \
    --attention-backend trtllm_mla \
    --speculative-draft-attention-backend fa4 \
    --mem-fraction-static 0.9 \
    --speculative-dflash-draft-window-size 4096 \
    --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

from openai import OpenAI
client = OpenAI(base_url="http://localhost:30000/v1", api_key="EMPTY")
response = client.chat.completions.create(
    model="moonshotai/Kimi-K2.5",
    messages=[{"role": "user", "content": "Write a quicksort in Python."}],
    max_tokens=4096,
)
print(response.choices[0].message.content)

Benchmark Results

Acceptance Length

• Thinking: enabled
• Max new tokens: 4096
• Block size: 8
• SGLang results.

Throughput

Acknowledgements

Special thanks to David Wang for his outstanding engineering support on this project. We are also grateful to Modal , InnoMatrix , and Yotta Labs 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 .

@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}
}