Search Results for author:
Found 2 papers, 0 papers with code
LCQ: Low-Rank Codebook based Quantization for Large Language Models
Weight quantization has been widely used for model compression, which can reduce both storage and computational cost.
Weight Normalization based Quantization for Deep Neural Network Compression
WNQ adopts weight normalization to avoid the long-tail distribution of network weights and subsequently reduces the quantization error.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
