Adaptive Draft Sequence Length: Enhancing Speculative Decoding Throughput on PIM-Enabled Systems.
Runze Wang, Qinggang Wang, Haifeng Liu, Long Zheng, Xiaofei Liao, Hai Jin, Jingling Xue
Browse the full HPCA paper archive.
Runze Wang, Qinggang Wang, Haifeng Liu, Long Zheng, Xiaofei Liao, Hai Jin, Jingling Xue
Browse the full HPCA paper archive.