z-lab/dflash
DFlash: Block Diffusion for Flash Speculative DecodingDFlash: Block Diffusion for Flash Speculative Decoding Paper | Blog | Models DFlash is a lightweight block diffusion model designed for speculative decoding. It enables efficient and high-quality parallel drafting. https://github.com/user-attachments/assets/5b29cabb-eb95-44c9-8ffe-367c0758de8c Supported Models Model DFlash Draft gemma-4-26B-A4B-it z-lab/gemma-4-26B-A4B-it-DFlash gemma-4-31B-it z-lab/gemma-4-31B-it-DFlash Qwen3.6-27B z-lab/Qwe...
Read full article →