Showing 2024Show all
2 papers · 1 filter
cs.CL2024
Enhancing One-shot Pruned Pre-trained Language Models through Sparse-Dense-Sparse Mechanism
Guanchen Li, Xiandong Zhao, Lian Liu +6
Pre-trained language models (PLMs) are engineered to be robust in contextual understanding and exhibit outstanding performance in various natural language processing tasks. However…
cs.AI2024
Amphista: Bi-directional Multi-head Decoding for Accelerating LLM Inference
Zeping Li, Xinlong Yang, Ziheng Gao +7
Large Language Models (LLMs) inherently use autoregressive decoding, which lacks parallelism in inference and results in significantly slow inference speed. While methods such as M…