{"id":"doi:10.1145/3714983.3714987","kind":"article","title":"AWQ: Activation-aware Weight Quantization for On-Device LLM Compression and Acceleration","authors":["Ji Lin","Jiaming Tang","Haotian Tang","Shang Wen Yang","Guangxuan Xiao","Song Han"],"author_count":6,"year":2025,"published":"2025-01-20","venue":"GetMobile Mobile Computing and Communications","cited_by":274,"doi":"10.1145/3714983.3714987","arxiv_id":null,"nct_id":null,"source_url":"https://doi.org/10.1145/3714983.3714987","archive_url":"https://space-kitty.com/papers/doi:10.1145/3714983.3714987","updated":null,"pmid":null,"pmcid":null,"openalex_id":"W4406650295","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":[]}