{"id":"https://openalex.org/W4402897014","doi":"https://doi.org/10.1109/iwqos61813.2024.10682928","title":"GreenLLM: Towards Efficient Large Language Model via Energy-aware Pruning","display_name":"GreenLLM: Towards Efficient Large Language Model via Energy-aware Pruning","publication_year":2024,"publication_date":"2024-06-19","ids":{"openalex":"https://openalex.org/W4402897014","doi":"https://doi.org/10.1109/iwqos61813.2024.10682928"},"language":"en","primary_location":{"id":"doi:10.1109/iwqos61813.2024.10682928","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iwqos61813.2024.10682928","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/ACM 32nd International Symposium on Quality of Service (IWQoS)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002237286","display_name":"Chunlin Tian","orcid":"https://orcid.org/0000-0002-1401-2032"},"institutions":[{"id":"https://openalex.org/I204512498","display_name":"University of Macau","ror":"https://ror.org/01r4q9n85","country_code":"MO","type":"education","lineage":["https://openalex.org/I204512498"]}],"countries":["MO"],"is_corresponding":true,"raw_author_name":"Chunlin Tian","raw_affiliation_strings":["University of Macau, IOTSC"],"affiliations":[{"raw_affiliation_string":"University of Macau, IOTSC","institution_ids":["https://openalex.org/I204512498"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104297735","display_name":"Xinpeng Qin","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinpeng Qin","raw_affiliation_strings":["University of Electronic Science and Technology of China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100361230","display_name":"Li Li","orcid":"https://orcid.org/0000-0002-7163-6263"},"institutions":[{"id":"https://openalex.org/I204512498","display_name":"University of Macau","ror":"https://ror.org/01r4q9n85","country_code":"MO","type":"education","lineage":["https://openalex.org/I204512498"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Li Li","raw_affiliation_strings":["University of Macau, IOTSC"],"affiliations":[{"raw_affiliation_string":"University of Macau, IOTSC","institution_ids":["https://openalex.org/I204512498"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5002237286"],"corresponding_institution_ids":["https://openalex.org/I204512498"],"apc_list":null,"apc_paid":null,"fwci":0.3376,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.66448594,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"2"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.6952000260353088,"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":0.6952000260353088,"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/computer-science","display_name":"Computer science","score":0.7585705518722534},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.699030339717865},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5859324932098389},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40560969710350037},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3613586127758026}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7585705518722534},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.699030339717865},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5859324932098389},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40560969710350037},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3613586127758026},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iwqos61813.2024.10682928","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iwqos61813.2024.10682928","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/ACM 32nd International Symposium on Quality of Service (IWQoS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.6000000238418579}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W2554302513","https://openalex.org/W3168867926","https://openalex.org/W6782879696","https://openalex.org/W6796581206","https://openalex.org/W6852962002"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W3204019825"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"GreenLLM,":[3],"a":[4,43,62,67],"framework":[5],"that":[6],"effectively":[7],"deploys":[8],"generative":[9],"Large":[10],"Language":[11],"Models":[12],"(LLMs)":[13],"on":[14,38],"resource-limited":[15],"edge":[16],"devices":[17],"to":[18,41,82,87],"well":[19],"meet":[20],"the":[21,74,84],"memory":[22],"and":[23,49],"timing":[24],"constraints":[25,52],"with":[26],"minimized":[27],"energy":[28,34],"consumption.":[29],"Specifically,":[30],"GreenLLM":[31],"employs":[32],"an":[33],"estimation":[35],"scheme":[36],"based":[37],"physical":[39],"hardware":[40],"guide":[42],"pruning-ratio":[44],"generator":[45],"incorporating":[46],"space,":[47],"weight,":[48],"power":[50],"(SWaP)":[51],"for":[53],"optimal":[54],"pruning":[55],"ratio.":[56],"For":[57],"each":[58],"layer,":[59],"we":[60,78],"employ":[61],"dependency-aware":[63],"energy-efficient":[64],"Pruner":[65],"in":[66],"task-agnostic":[68],"manner,":[69],"maximally":[70],"preserving":[71],"most":[72],"of":[73],"LLM":[75],"functionality.":[76],"Finally,":[77],"use":[79],"downstream":[80],"datasets":[81],"fine-tune":[83],"pruned":[85],"model":[86],"recover":[88],"performance.":[89]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-15T08:11:43.952461","created_date":"2025-10-10T00:00:00"}