Showing cs.LGShow all
2 papers · 1 filter
cs.LG2024
ASER: Activation Smoothing and Error Reconstruction for Large Language Model Quantization
Weibo Zhao, Yubin Shi, Xinyu Lyu +3
Quantization stands as a pivotal technique for large language model (LLM) serving, yet it poses significant challenges particularly in achieving effective low-bit quantization. The…
cs.LG2024
Train Faster, Perform Better: Modular Adaptive Training in Over-Parameterized Models
Yubin Shi, Yixuan Chen, Mingzhi Dong +10
Despite their prevalence in deep-learning communities, over-parameterized models convey high demands of computational costs for proper training. This work studies the fine-grained,…