{"id":"https://openalex.org/W7138402086","doi":"https://doi.org/10.18653/v1/2025.ijcnlp-long.10","title":"GQSA: Group Quantization and Sparsity for Accelerating Large Language Model Inference","display_name":"GQSA: Group Quantization and Sparsity for Accelerating Large Language Model Inference","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W7138402086","doi":"https://doi.org/10.18653/v1/2025.ijcnlp-long.10"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.ijcnlp-long.10","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.ijcnlp-long.10","pdf_url":"https://aclanthology.org/2025.ijcnlp-long.10.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.ijcnlp-long.10.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129707145","display_name":"Chao Zeng","orcid":null},"institutions":[{"id":"https://openalex.org/I2801694295","display_name":"Virginia Cooperative Extension","ror":"https://ror.org/0149vtr75","country_code":"US","type":"education","lineage":["https://openalex.org/I2801694295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chao Zeng","raw_affiliation_strings":["ByteDance Inc ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Inc ,","institution_ids":["https://openalex.org/I2801694295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129740558","display_name":"Songwei Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I2801694295","display_name":"Virginia Cooperative Extension","ror":"https://ror.org/0149vtr75","country_code":"US","type":"education","lineage":["https://openalex.org/I2801694295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Songwei Liu","raw_affiliation_strings":["ByteDance Inc ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Inc ,","institution_ids":["https://openalex.org/I2801694295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129656778","display_name":"Shu Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I2801694295","display_name":"Virginia Cooperative Extension","ror":"https://ror.org/0149vtr75","country_code":"US","type":"education","lineage":["https://openalex.org/I2801694295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shu Yang","raw_affiliation_strings":["ByteDance Inc ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Inc ,","institution_ids":["https://openalex.org/I2801694295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122054829","display_name":"Fangmin Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I2801694295","display_name":"Virginia Cooperative Extension","ror":"https://ror.org/0149vtr75","country_code":"US","type":"education","lineage":["https://openalex.org/I2801694295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fangmin Chen","raw_affiliation_strings":["ByteDance Inc ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Inc ,","institution_ids":["https://openalex.org/I2801694295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129736307","display_name":"Xing Mei","orcid":null},"institutions":[{"id":"https://openalex.org/I2801694295","display_name":"Virginia Cooperative Extension","ror":"https://ror.org/0149vtr75","country_code":"US","type":"education","lineage":["https://openalex.org/I2801694295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xing Mei","raw_affiliation_strings":["ByteDance Inc ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Inc ,","institution_ids":["https://openalex.org/I2801694295"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129702255","display_name":"Lean Fu","orcid":null},"institutions":[{"id":"https://openalex.org/I2801694295","display_name":"Virginia Cooperative Extension","ror":"https://ror.org/0149vtr75","country_code":"US","type":"education","lineage":["https://openalex.org/I2801694295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lean Fu","raw_affiliation_strings":["ByteDance Inc ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Inc ,","institution_ids":["https://openalex.org/I2801694295"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2801694295"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"149","last_page":"165"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.31769999861717224,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.31769999861717224,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.10019999742507935,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.08760000020265579,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.4729999899864197},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.44339999556541443},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.42419999837875366},{"id":"https://openalex.org/keywords/group","display_name":"Group (periodic table)","score":0.313400000333786},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.2696000039577484}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6033999919891357},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4966999888420105},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.4729999899864197},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.44339999556541443},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.42419999837875366},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.42320001125335693},{"id":"https://openalex.org/C2781311116","wikidata":"https://www.wikidata.org/wiki/Q83306","display_name":"Group (periodic table)","level":2,"score":0.313400000333786},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2985999882221222},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2865999937057495},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2696000039577484},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.2678000032901764},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.26010000705718994},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.ijcnlp-long.10","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.ijcnlp-long.10","pdf_url":"https://aclanthology.org/2025.ijcnlp-long.10.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.ijcnlp-long.10","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.ijcnlp-long.10","pdf_url":"https://aclanthology.org/2025.ijcnlp-long.10.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138402086.pdf","grobid_xml":"https://content.openalex.org/works/W7138402086.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Chao":[0],"Zeng,":[1],"Songwei":[2],"Liu,":[3],"Shu":[4],"Yang,":[5],"Fangmin":[6],"Chen,":[7],"Xing":[8],"Mei,":[9],"Lean":[10],"Fu.":[11],"Proceedings":[12],"of":[13,27,31],"the":[14,24,28,32],"14th":[15],"International":[16],"Joint":[17],"Conference":[18,26],"on":[19],"Natural":[20],"Language":[21],"Processing":[22],"and":[23],"4th":[25],"Asia-Pacific":[29],"Chapter":[30],"Association":[33],"for":[34],"Computational":[35],"Linguistics.":[36],"2025.":[37]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-18T00:00:00"}