Mingyu Gao

Accelerating Large-Scale Reasoning Model Inference with Sparse Self-Speculative Decoding

Yilong Zhao, Jiaming Tang, Kan Zhu, Zihao Ye, Chi-Chih Chang, Chih‐Jen Lin, Jongseok Park, Guangxuan Xiao, Mohamed S. Abdelfattah, Mingyu Gao, Baris Kasikci, Song Han, Ion Stoica (2025). Accelerating Large-Scale Reasoning Model Inference with Sparse Self-Speculative Decoding. , DOI: https://doi.org/10.48550/arxiv.2512.01278.