McPAL: Scaling Unstructured Sparse Inference with Multi-Chiplet HBM-PIM Architecture for LLMs.
Shiwei Liu, Zhirui Huang, Jiangnan Yu, Qi Liu, Chixiao Chen
Browse the full DAC paper archive.
Shiwei Liu, Zhirui Huang, Jiangnan Yu, Qi Liu, Chixiao Chen
Browse the full DAC paper archive.