PipeDec: Low-Latency Pipeline-based Inference with Dynamic Speculative Decoding Towards Large-scale Models Haofei Yin,Mengbai Xiao, Rouzhou Lu,Xiao Zhang,Dongxiao Yu,Guanghui Zhangarxiv(2025)引用 0|浏览5AI 理解论文溯源树样例生成溯源树,研究论文发展脉络Chat Paper正在生成论文摘要