{"id":"doi:10.1109/tcsi.2024.3350661","kind":"article","title":"Quantization and Hardware Architecture Co-Design for Matrix-Vector Multiplications of Large Language Models","authors":["Wenjie Li","Aokun Hu","Ningyi Xu","Guanghui He"],"author_count":4,"year":2024,"published":"2024-01-15","venue":"IEEE Transactions on Circuits and Systems I Regular Papers","cited_by":24,"doi":"10.1109/tcsi.2024.3350661","arxiv_id":null,"nct_id":null,"source_url":"https://doi.org/10.1109/tcsi.2024.3350661","archive_url":"https://space-kitty.com/papers/doi:10.1109/tcsi.2024.3350661","updated":null,"pmid":null,"pmcid":null,"openalex_id":"W4390871466","pdf_url":null,"abstract":null,"abstract_license":null,"license":null,"is_open_access":false,"retracted":false,"peer_reviewed":null,"categories":["Advanced Neural Network Applications"],"details":null,"provenance":"openalex","attribution":"Metadata and citation counts: OpenAlex (CC0).","topics":[{"slug":"efficient-ai","name":"Efficient Training & Inference","domain_slug":"ai"}],"cited_in_dossiers":[]}