Alpamayo 1 (R1) — DFlash draft

Flash Vision-Language-Action Inference for Autonomous Driving

DFlash draft model for z-lab/Alpamayo-R1-10B, used by FlashDrive to accelerate the chain-of-causation reasoning of Alpamayo 1 (R1).

DFlash (ICML 2026) uses a lightweight block-diffusion draft to propose several tokens in parallel; the target verifies each block in a single forward, preserving its output distribution. This draft is a 2-layer Qwen3-style network (block size 8) conditioned on target hidden states from layers 24/30/31/32/34. The repository also ships mask_embedding.pt, the trained mask-token embedding FlashDrive appends to the target's embedding table.

Not a standalone language model. FlashDrive attaches it to the base checkpoint automatically — you do not load this repository directly.

Usage

import flashdrive

# from_pretrained fetches this -DFlash checkpoint automatically
model = flashdrive.from_pretrained("z-lab/Alpamayo-R1-10B")

See the base model card and the FlashDrive repository for the full pipeline.

License

This checkpoint is derived from NVIDIA's Alpamayo weights and is governed by the NVIDIA License, which permits non-commercial use only and extends to derivative works. The FlashDrive inference code is separately released under the MIT License.

Citation

@inproceedings{chen2026dflash,
  title     = {{DFlash: Block Diffusion for Flash Speculative Decoding}},
  author    = {Chen, Jian and Liang, Yesheng and Liu, Zhijian},
  booktitle = {International Conference on Machine Learning (ICML)},
  year      = {2026}
}

@article{li2026flashdrive,
  title  = {{FlashDrive: Flash Vision-Language-Action Inference for Autonomous Driving}},
  author = {Li, Zekai and Liang, Yihao and Zhang, Hongfei and Chen, Jian and Liang, Yesheng and Liu, Zhijian},
  year   = {2026}
}