DFlash: Block Diffusion for Flash Speculative Decoding 事件

DFlash: Block Diffusion for Flash Speculative Decoding arXiv:2602.06036v2 Announce Type: replace Abstract: Autoregressive large language models (LLMs) deliver strong performance but require inherently sequential decoding, leading to high inference latency and poor GPU utilization. Speculative decoding mitigates this bottleneck by using a fast draft model whose outputs are verified in parallel by the target LLM; however, existing methods still rely on autoregressive drafting, which remains seque