1
DFlare: Scaling Up Draft Capacity for Block Diffusion Speculative Decoding
LLM推理新突破：块扩散推测解码通过同时预测整个块来加速验证，提升模型效率
arXiv:2606.02091v1 Announce Type: new Abstract: Block diffusion speculative decoding accelerates LLM inference by predicting all tokens within a block…