{"id":"https://openalex.org/W4406892430","doi":"https://doi.org/10.1109/fllm63129.2024.10852499","title":"Methodologies for Selecting Optimal Hardware for Locally Deployed LLMs Using a Performance, Accuracy and Cost (PAC) Approach","display_name":"Methodologies for Selecting Optimal Hardware for Locally Deployed LLMs Using a Performance, Accuracy and Cost (PAC) Approach","publication_year":2024,"publication_date":"2024-11-26","ids":{"openalex":"https://openalex.org/W4406892430","doi":"https://doi.org/10.1109/fllm63129.2024.10852499"},"language":"en","primary_location":{"id":"doi:10.1109/fllm63129.2024.10852499","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fllm63129.2024.10852499","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 2nd International Conference on Foundation and Large Language Models (FLLM)","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/A5047504393","display_name":"Kuan Heng Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I4210158342","display_name":"Intel (United Kingdom)","ror":"https://ror.org/058cxws58","country_code":"GB","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210158342"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Kuan Heng Lee","raw_affiliation_strings":["Intel Corporation"],"affiliations":[{"raw_affiliation_string":"Intel Corporation","institution_ids":["https://openalex.org/I4210158342"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028499291","display_name":"Mee Sim Lai","orcid":null},"institutions":[{"id":"https://openalex.org/I4210158342","display_name":"Intel (United Kingdom)","ror":"https://ror.org/058cxws58","country_code":"GB","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210158342"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mee Sim Lai","raw_affiliation_strings":["Intel Corporation"],"affiliations":[{"raw_affiliation_string":"Intel Corporation","institution_ids":["https://openalex.org/I4210158342"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014399174","display_name":"Shin Wei Lim","orcid":"https://orcid.org/0000-0002-2580-4051"},"institutions":[{"id":"https://openalex.org/I4210158342","display_name":"Intel (United Kingdom)","ror":"https://ror.org/058cxws58","country_code":"GB","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210158342"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Shin Wei Lim","raw_affiliation_strings":["Intel Corporation"],"affiliations":[{"raw_affiliation_string":"Intel Corporation","institution_ids":["https://openalex.org/I4210158342"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116057023","display_name":"Jocelyn Shuang Ru Teh","orcid":null},"institutions":[{"id":"https://openalex.org/I4210158342","display_name":"Intel (United Kingdom)","ror":"https://ror.org/058cxws58","country_code":"GB","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210158342"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jocelyn Shuang Ru Teh","raw_affiliation_strings":["Intel Corporation"],"affiliations":[{"raw_affiliation_string":"Intel Corporation","institution_ids":["https://openalex.org/I4210158342"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116057024","display_name":"Syafie Nizam","orcid":null},"institutions":[{"id":"https://openalex.org/I4210158342","display_name":"Intel (United Kingdom)","ror":"https://ror.org/058cxws58","country_code":"GB","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210158342"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Syafie Nizam","raw_affiliation_strings":["Intel Corporation"],"affiliations":[{"raw_affiliation_string":"Intel Corporation","institution_ids":["https://openalex.org/I4210158342"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116057025","display_name":"Yuan Kuok Nee","orcid":null},"institutions":[{"id":"https://openalex.org/I4210158342","display_name":"Intel (United Kingdom)","ror":"https://ror.org/058cxws58","country_code":"GB","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210158342"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yuan Kuok Nee","raw_affiliation_strings":["Intel Corporation"],"affiliations":[{"raw_affiliation_string":"Intel Corporation","institution_ids":["https://openalex.org/I4210158342"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116057026","display_name":"Eng Keong Koay","orcid":null},"institutions":[{"id":"https://openalex.org/I4210158342","display_name":"Intel (United Kingdom)","ror":"https://ror.org/058cxws58","country_code":"GB","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210158342"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Eng Keong Koay","raw_affiliation_strings":["Intel Corporation"],"affiliations":[{"raw_affiliation_string":"Intel Corporation","institution_ids":["https://openalex.org/I4210158342"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5116057027","display_name":"Meng Siong Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I4210158342","display_name":"Intel (United Kingdom)","ror":"https://ror.org/058cxws58","country_code":"GB","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210158342"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Meng Siong Lee","raw_affiliation_strings":["Intel Corporation"],"affiliations":[{"raw_affiliation_string":"Intel Corporation","institution_ids":["https://openalex.org/I4210158342"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5047504393"],"corresponding_institution_ids":["https://openalex.org/I4210158342"],"apc_list":null,"apc_paid":null,"fwci":0.4175,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.64608183,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"362","last_page":"369"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11522","display_name":"VLSI and FPGA Design Techniques","score":0.9696999788284302,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/T11522","display_name":"VLSI and FPGA Design Techniques","score":0.9696999788284302,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9397000074386597,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9390000104904175,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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":0.6908616423606873}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6908616423606873}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/fllm63129.2024.10852499","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fllm63129.2024.10852499","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 2nd International Conference on Foundation and Large Language Models (FLLM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":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":{"The":[0],"rapid":[1],"advancement":[2],"of":[3,66],"Large":[4],"Language":[5],"Models":[6],"(LLMs)":[7],"has":[8],"significantly":[9],"impacted":[10],"computational":[11,124],"linguistics,":[12],"transitioning":[13],"from":[14],"predominantly":[15],"closed-source,":[16],"cloud-based":[17],"models":[18],"to":[19,87],"open-source":[20],"solutions":[21],"deployed":[22],"on":[23,45,62,80],"edge":[24,115],"devices.":[25,47],"This":[26,48],"shift":[27],"addresses":[28],"concerns":[29],"over":[30],"data":[31],"privacy,":[32],"infrastructure":[33],"costs,":[34],"and":[35,69,82,120],"vendor":[36],"lock-in":[37],"but":[38],"introduces":[39],"unique":[40],"challenges":[41],"for":[42,53,58,109,122],"deploying":[43],"LLMs":[44],"resource-constrained":[46],"paper":[49],"presents":[50],"a":[51,63,97],"methodology":[52],"selecting":[54,110],"cost-effective":[55],"hardware":[56],"platforms":[57],"LLM":[59],"deployment,":[60],"focusing":[61,79],"balanced":[64],"assessment":[65],"Performance,":[67],"Accuracy,":[68],"Cost":[70],"(PAC).":[71],"Our":[72],"approach":[73],"reveals":[74],"that":[75,114],"while":[76],"traditional":[77],"methods":[78],"performance":[81],"cost":[83],"alone":[84],"may":[85],"lead":[86],"suboptimal":[88],"choices,":[89],"incorporating":[90],"accuracy":[91],"into":[92],"the":[93],"PAC":[94],"framework":[95],"provides":[96],"more":[98],"comprehensive":[99],"evaluation.":[100],"By":[101],"applying":[102],"this":[103],"methodology,":[104],"we":[105],"offer":[106],"practical":[107],"guidance":[108],"optimal":[111],"infrastructure,":[112],"ensuring":[113],"deployments":[116],"are":[117],"both":[118],"efficient":[119],"effective":[121],"various":[123],"linguistics":[125],"applications.":[126]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-29T08:15:47.926485","created_date":"2025-10-10T00:00:00"}