{"id":"https://openalex.org/W4396709386","doi":"https://doi.org/10.1145/3629526.3645045","title":"Leftovers for LLaMA","display_name":"Leftovers for LLaMA","publication_year":2024,"publication_date":"2024-05-06","ids":{"openalex":"https://openalex.org/W4396709386","doi":"https://doi.org/10.1145/3629526.3645045"},"language":"en","primary_location":{"id":"doi:10.1145/3629526.3645045","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3629526.3645045","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3629526.3645045","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th ACM/SPEC International Conference on Performance Engineering","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3629526.3645045","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012558920","display_name":"Ravi Kumar Singh","orcid":"https://orcid.org/0009-0009-9547-5968"},"institutions":[{"id":"https://openalex.org/I55215948","display_name":"Tata Consultancy Services (India)","ror":"https://ror.org/01b9n8m42","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210086519","https://openalex.org/I55215948"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Ravi Kumar Singh","raw_affiliation_strings":["TCS Research, Thane, India"],"affiliations":[{"raw_affiliation_string":"TCS Research, Thane, India","institution_ids":["https://openalex.org/I55215948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5096717936","display_name":"Likhith Bandamudi","orcid":null},"institutions":[{"id":"https://openalex.org/I55215948","display_name":"Tata Consultancy Services (India)","ror":"https://ror.org/01b9n8m42","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210086519","https://openalex.org/I55215948"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Likhith Bandamudi","raw_affiliation_strings":["TCS Research, Thane, India"],"affiliations":[{"raw_affiliation_string":"TCS Research, Thane, India","institution_ids":["https://openalex.org/I55215948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085697832","display_name":"Shruti Kunde","orcid":"https://orcid.org/0000-0002-4708-0496"},"institutions":[{"id":"https://openalex.org/I55215948","display_name":"Tata Consultancy Services (India)","ror":"https://ror.org/01b9n8m42","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210086519","https://openalex.org/I55215948"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Shruti Kunde","raw_affiliation_strings":["TCS Research, Mumbai, India"],"affiliations":[{"raw_affiliation_string":"TCS Research, Mumbai, India","institution_ids":["https://openalex.org/I55215948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101566702","display_name":"Mayank Mishra","orcid":"https://orcid.org/0000-0002-4654-1246"},"institutions":[{"id":"https://openalex.org/I55215948","display_name":"Tata Consultancy Services (India)","ror":"https://ror.org/01b9n8m42","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210086519","https://openalex.org/I55215948"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Mayank Mishra","raw_affiliation_strings":["TCS Research, Thane, India"],"affiliations":[{"raw_affiliation_string":"TCS Research, Thane, India","institution_ids":["https://openalex.org/I55215948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086400313","display_name":"Rekha Singhal","orcid":"https://orcid.org/0000-0002-3712-1784"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rekha Singhal","raw_affiliation_strings":["TCS Research, Paceport, NY, USA"],"affiliations":[{"raw_affiliation_string":"TCS Research, Paceport, NY, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5012558920"],"corresponding_institution_ids":["https://openalex.org/I55215948"],"apc_list":null,"apc_paid":null,"fwci":0.7252,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.73710154,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"201","last_page":"210"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9993000030517578,"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":0.9993000030517578,"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9976000189781189,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9954000115394592,"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":0.8169487714767456},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.728921115398407},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.5915167927742004},{"id":"https://openalex.org/keywords/server","display_name":"Server","score":0.5502972602844238},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5488576889038086},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.499558687210083},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4513791799545288},{"id":"https://openalex.org/keywords/computer-cluster","display_name":"Computer cluster","score":0.4323425889015198},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.2769519090652466},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.19372335076332092},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.16982656717300415},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.16672378778457642}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8169487714767456},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.728921115398407},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5915167927742004},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.5502972602844238},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5488576889038086},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.499558687210083},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4513791799545288},{"id":"https://openalex.org/C29140674","wikidata":"https://www.wikidata.org/wiki/Q206637","display_name":"Computer cluster","level":2,"score":0.4323425889015198},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.2769519090652466},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.19372335076332092},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.16982656717300415},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.16672378778457642},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3629526.3645045","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3629526.3645045","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3629526.3645045","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th ACM/SPEC International Conference on Performance Engineering","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3629526.3645045","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3629526.3645045","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3629526.3645045","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th ACM/SPEC International Conference on Performance Engineering","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.550000011920929,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4396709386.pdf"},"referenced_works_count":6,"referenced_works":["https://openalex.org/W2066700399","https://openalex.org/W2135774416","https://openalex.org/W3081168214","https://openalex.org/W4321153003","https://openalex.org/W4321636575","https://openalex.org/W4385570483"],"related_works":["https://openalex.org/W4288365749","https://openalex.org/W2936497627","https://openalex.org/W3013624417","https://openalex.org/W4287826556","https://openalex.org/W3098382480","https://openalex.org/W4287598411","https://openalex.org/W3094871513","https://openalex.org/W3100913109","https://openalex.org/W3198458223","https://openalex.org/W3126642501"],"abstract_inverted_index":{"n":[0],"recent":[1],"years,":[2],"large":[3,76,128,207,240],"language":[4,129,208,241],"models":[5,42,77,92,209,242],"(LLMs)":[6],"have":[7],"become":[8],"pervasive":[9],"in":[10,29,93],"our":[11,199],"day-to-day":[12],"lives,":[13],"with":[14,63,163],"enterprises":[15],"utilizing":[16,40,148,232],"their":[17,103],"services":[18],"for":[19,38,43,89],"a":[20,35,48,87,94,109,115,127],"wide":[21],"range":[22],"of":[23,32,51,96,118,139,152,180,187,198,228,239],"NLP-based":[24],"applications.":[25],"The":[26],"exponential":[27],"growth":[28],"the":[30,137,143,149,153,178,181,185,196],"size":[31],"LLMs":[33],"poses":[34],"significant":[36],"challenge":[37,73],"efficiently":[39],"these":[41,79],"inference":[44],"tasks,":[45],"which":[46],"require":[47,99],"substantial":[49],"amount":[50],"memory":[52,160],"and":[53,214,218],"compute.":[54],"Enterprises":[55],"often":[56],"possess":[57],"multiple":[58],"resources":[59],"(workers,":[60],"nodes,":[61],"servers)":[62],"unused":[64],"(leftover)":[65],"capacity,":[66],"providing":[67],"an":[68],"opportunity":[69],"to":[70,105,114,135],"address":[71],"this":[72,121],"by":[74,147,183,201,231],"distributing":[75,90,168],"across":[78,172],"resources.":[80,97],"Recent":[81],"work":[82],"such":[83],"as":[84],"Petals,":[85],"provides":[86],"platform":[88],"LLM":[91],"cluster":[95],"Petals":[98],"that":[100,133,189,223],"users":[101],"use":[102],"discretion":[104],"distribute":[106],"blocks":[107,141,170,230],"on":[108,142],"given":[110],"cluster,":[111],"consequently":[112],"leading":[113],"non-optimal":[116],"placement":[117,131,138,227],"blocks.":[119],"In":[120],"paper,":[122],"we":[123,176],"propose":[124],"LLaMPS":[125,224],"-":[126,210],"model":[130],"system":[132,182],"aims":[134],"optimize":[136],"transformer":[140,169,229],"available":[144,164],"enterprise":[145],"resources,":[146,234],"leftover":[150,159,233],"capacity":[151,161],"worker":[154,173],"nodes.":[155,174],"Our":[156,220],"approach":[157,200],"considers":[158],"along":[162],"CPU":[165],"cores,":[166],"when":[167],"optimally":[171],"Furthermore,":[175],"enhance":[177],"scalability":[179],"maximizing":[184],"number":[186],"clients":[188],"can":[190],"be":[191],"served":[192],"concurrently.":[193],"We":[194],"validate":[195],"efficacy":[197],"conducting":[202],"extensive":[203],"experiments":[204,221],"using":[205],"open-source":[206],"BLOOM":[211],"(1b,":[212],"3b,":[213],"7b":[215],"parameters),":[216],"Falcon,":[217],"LLaMA.":[219],"demonstrate":[222],"facilitates":[225],"optimal":[226],"thus":[235],"enabling":[236],"enterprise-level":[237],"deployment":[238]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}