Task Profiling and Draft Model Selection for Accelerating Distributed Speculative Decoding.
Jialin Dong, Yaodan Xu, Tan Chen, Sheng Zhou, Zhisheng Niu
Browse the full INFOCOM paper archive.
Jialin Dong, Yaodan Xu, Tan Chen, Sheng Zhou, Zhisheng Niu
Browse the full INFOCOM paper archive.