PDTrim: Targeted Pruning for Prefill-Decode Disaggregation in Inference.
Hao Zhang, Mengsi Lyu, Zhuo Chen, Yulong Ao, Yonghua Lin
Browse the full ACL paper archive.
Hao Zhang, Mengsi Lyu, Zhuo Chen, Yulong Ao, Yonghua Lin
Browse the full ACL paper archive.