{"id":"https://openalex.org/W4413680160","doi":"https://doi.org/10.1109/compsac65507.2025.00224","title":"Optimizing LLMs for Resource-Constrained Environments: A Survey of Model Compression Techniques","display_name":"Optimizing LLMs for Resource-Constrained Environments: A Survey of Model Compression Techniques","publication_year":2025,"publication_date":"2025-07-08","ids":{"openalex":"https://openalex.org/W4413680160","doi":"https://doi.org/10.1109/compsac65507.2025.00224"},"language":"en","primary_location":{"id":"doi:10.1109/compsac65507.2025.00224","is_oa":false,"landing_page_url":"https://doi.org/10.1109/compsac65507.2025.00224","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 49th Annual Computers, Software, and Applications Conference (COMPSAC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2505.02309","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000905456","display_name":"Sanjay Surendranath Girija","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sanjay Surendranath Girija","raw_affiliation_strings":["Google"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5118180027","display_name":"Lakshit Arora","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lakshit Arora","raw_affiliation_strings":["Google"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081111343","display_name":"Shashank Kapoor","orcid":"https://orcid.org/0009-0006-1277-294X"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shashank Kapoor","raw_affiliation_strings":["Google"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Dipen Pradhan","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dipen Pradhan","raw_affiliation_strings":["Google"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033190244","display_name":"Abhishek Raj","orcid":"https://orcid.org/0000-0002-7768-6499"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aman Raj","raw_affiliation_strings":["Google"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5118120013","display_name":"Ankit Shetgaonkar","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ankit Shetgaonkar","raw_affiliation_strings":["Google"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5000905456"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":2.2595,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.89333184,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1657","last_page":"1664"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9297000169754028,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9297000169754028,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6315086483955383},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.5030061602592468},{"id":"https://openalex.org/keywords/resource-management","display_name":"Resource management (computing)","score":0.431861937046051},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.4278140664100647},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.1838204264640808},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.07171836495399475}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6315086483955383},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.5030061602592468},{"id":"https://openalex.org/C2780609101","wikidata":"https://www.wikidata.org/wiki/Q17156588","display_name":"Resource management (computing)","level":2,"score":0.431861937046051},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.4278140664100647},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.1838204264640808},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.07171836495399475},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/compsac65507.2025.00224","is_oa":false,"landing_page_url":"https://doi.org/10.1109/compsac65507.2025.00224","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 49th Annual Computers, Software, and Applications Conference (COMPSAC)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2505.02309","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.02309","pdf_url":"https://arxiv.org/pdf/2505.02309","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2505.02309","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.02309","pdf_url":"https://arxiv.org/pdf/2505.02309","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"have":[4],"revolutionized":[5],"many":[6],"areas":[7],"of":[8,32,70],"artificial":[9],"intelligence":[10],"(AI),":[11],"but":[12],"their":[13,18],"substantial":[14],"resource":[15,96],"requirements":[16],"limit":[17],"deployment":[19],"on":[20],"mobile":[21],"and":[22,53,67,82,100],"edge":[23,107],"devices.":[24],"This":[25],"survey":[26],"paper":[27],"provides":[28],"a":[29,94],"comprehensive":[30],"overview":[31],"techniques":[33,78],"for":[34,97,106],"compressing":[35],"LLMs":[36,105],"to":[37,92,103],"enable":[38],"efficient":[39],"inference":[40],"in":[41],"resource-constrained":[42],"environments.":[43],"We":[44,73],"examine":[45],"three":[46],"primary":[47],"approaches:":[48],"Knowledge":[49],"Distillation,":[50],"Model":[51,54],"Quantization,":[52],"Pruning.":[55],"For":[56],"each":[57],"technique,":[58],"we":[59,86],"discuss":[60,76],"the":[61],"underlying":[62],"principles,":[63],"present":[64],"different":[65],"variants,":[66],"provide":[68,93],"examples":[69],"successful":[71],"applications.":[72],"also":[74],"briefly":[75],"complementary":[77],"such":[79],"as":[80],"mixture-of-experts":[81],"early-exit":[83],"strategies.":[84],"Finally,":[85],"highlight":[87],"promising":[88],"future":[89],"directions,":[90],"aiming":[91],"valuable":[95],"both":[98],"researchers":[99],"practitioners":[101],"seeking":[102],"optimize":[104],"deployment.":[108]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-04-17T18:11:37.981687","created_date":"2025-10-10T00:00:00"}