TopGQ: Fast GNN Post-Training Quantization Leveraging Topology Information
TopGQ, an accurate post-training GNN quantization framework, alleviating redundant quantization overhead, is presented, and dual-axis scale absorption is proposed, which enables activation quantization along both the outer and inner dimensions by merging one into the adjacency matrix.
Dain Kwon, Kanghyun Choi, Hyeyoon Lee et al.
· 0 citations