Position-Aware Depth Decay Decoding (D³): Boosting Large Language Model Inference Efficiency.
Siqi Fan, Xuezhi Fang, Xingrun Xing, Peng Han, Shuo Shang, Yequan Wang
Browse the full ACL paper archive.
Siqi Fan, Xuezhi Fang, Xingrun Xing, Peng Han, Shuo Shang, Yequan Wang
Browse the full ACL paper archive.