{"id":"https://openalex.org/W4415821280","doi":"https://doi.org/10.1109/lca.2025.3628325","title":"LLMServingSim2.0: A Unified Simulator for Heterogeneous Hardware and Serving Techniques in LLM Infrastructure","display_name":"LLMServingSim2.0: A Unified Simulator for Heterogeneous Hardware and Serving Techniques in LLM Infrastructure","publication_year":2025,"publication_date":"2025-07-01","ids":{"openalex":"https://openalex.org/W4415821280","doi":"https://doi.org/10.1109/lca.2025.3628325"},"language":null,"primary_location":{"id":"doi:10.1109/lca.2025.3628325","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lca.2025.3628325","pdf_url":null,"source":{"id":"https://openalex.org/S17643076","display_name":"IEEE Computer Architecture Letters","issn_l":"1556-6056","issn":["1556-6056","1556-6064","2473-2575"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Computer Architecture Letters","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2511.07229","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029070493","display_name":"Jaehong Cho","orcid":"https://orcid.org/0009-0008-8973-5164"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Jaehong Cho","raw_affiliation_strings":["School of Computing, Korea Advanced Institute of Science and Technology, Daejeon, South Korea"],"affiliations":[{"raw_affiliation_string":"School of Computing, Korea Advanced Institute of Science and Technology, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hyunmin Choi","orcid":"https://orcid.org/0009-0002-4116-3896"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyunmin Choi","raw_affiliation_strings":["School of Computing, Korea Advanced Institute of Science and Technology, Daejeon, South Korea"],"affiliations":[{"raw_affiliation_string":"School of Computing, Korea Advanced Institute of Science and Technology, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037553165","display_name":"Jongse Park","orcid":"https://orcid.org/0000-0002-6629-449X"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jongse Park","raw_affiliation_strings":["School of Computing, Korea Advanced Institute of Science and Technology, Daejeon, South Korea"],"affiliations":[{"raw_affiliation_string":"School of Computing, Korea Advanced Institute of Science and Technology, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5029070493"],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.3673643,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"24","issue":"2","first_page":"361","last_page":"364"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.3831000030040741,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.3831000030040741,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.22190000116825104,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.16110000014305115,"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/key","display_name":"Key (lock)","score":0.6248000264167786},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5823000073432922},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.5116999745368958},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.3725999891757965},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.3677000105381012},{"id":"https://openalex.org/keywords/service","display_name":"Service (business)","score":0.3472000062465668}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8201000094413757},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6248000264167786},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.5898000001907349},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5823000073432922},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.5116999745368958},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4672999978065491},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.3725999891757965},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.36880001425743103},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.3677000105381012},{"id":"https://openalex.org/C2780378061","wikidata":"https://www.wikidata.org/wiki/Q25351891","display_name":"Service (business)","level":2,"score":0.3472000062465668},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.3434999883174896},{"id":"https://openalex.org/C201203610","wikidata":"https://www.wikidata.org/wiki/Q5157524","display_name":"Computer architecture simulator","level":2,"score":0.3077999949455261},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.30630001425743103},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.2709999978542328},{"id":"https://openalex.org/C65232700","wikidata":"https://www.wikidata.org/wiki/Q5656403","display_name":"Hardware architecture","level":3,"score":0.2653999924659729},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.2653000056743622},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.26109999418258667},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.25600001215934753}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/lca.2025.3628325","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lca.2025.3628325","pdf_url":null,"source":{"id":"https://openalex.org/S17643076","display_name":"IEEE Computer Architecture Letters","issn_l":"1556-6056","issn":["1556-6056","1556-6064","2473-2575"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Computer Architecture Letters","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2511.07229","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.07229","pdf_url":"https://arxiv.org/pdf/2511.07229","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:2511.07229","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.07229","pdf_url":"https://arxiv.org/pdf/2511.07229","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":[{"id":"https://openalex.org/G1407225476","display_name":null,"funder_award_id":"RS-2022-II221037","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G2638105757","display_name":null,"funder_award_id":"RS-2025-02305453","funder_id":"https://openalex.org/F4320322093","funder_display_name":"Electronics and Telecommunications Research Institute"},{"id":"https://openalex.org/G342704958","display_name":null,"funder_award_id":"funded","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G3946644632","display_name":null,"funder_award_id":"RS-2024-00342148","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G4700831490","display_name":null,"funder_award_id":"2022-","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G515828364","display_name":null,"funder_award_id":"No. RS-","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G6021319658","display_name":null,"funder_award_id":"RS-2024-003960","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G6072120315","display_name":null,"funder_award_id":"funded","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"}],"funders":[{"id":"https://openalex.org/F4320317879","display_name":"SK Hynix","ror":null},{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320322093","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415821280.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"LLMServingSim2.0,":[3],"a":[4,39,48,89,111,152],"system":[5],"simulator":[6],"designed":[7],"for":[8,102,155],"exploring":[9],"heterogeneous":[10],"hardware":[11,27,130,157],"in":[12,63],"large-scale":[13],"LLM":[14,65,140,160],"serving":[15,52,96,141],"systems.":[16],"LLMServingSim2.0":[17,71,137],"addresses":[18],"two":[19],"key":[20],"limitations":[21],"of":[22,38,51,61,85],"its":[23],"predecessor:":[24],"(1)":[25],"integrating":[26],"models":[28],"into":[29],"system-level":[30],"simulators":[31,45],"is":[32],"non-trivial":[33],"due":[34],"to":[35],"the":[36,59,83,123],"lack":[37],"clear":[40],"abstraction,":[41],"and":[42,107,121,159],"(2)":[43],"existing":[44],"support":[46],"only":[47],"narrow":[49],"subset":[50],"techniques,":[53],"leaving":[54],"no":[55],"infrastructure":[56],"that":[57,136],"captures":[58],"breadth":[60],"approaches":[62],"modern":[64],"serving.":[66],"To":[67],"overcome":[68],"these":[69],"issues,":[70],"adopts":[72],"trace-driven":[73],"performance":[74],"modeling,":[75],"accompanied":[76],"by":[77],"an":[78],"operator-level":[79],"latency":[80],"profiler,":[81],"enabling":[82],"integration":[84],"new":[86],"accelerators":[87],"with":[88,142],"single":[90],"command.":[91],"It":[92],"further":[93,134],"embeds":[94],"up-to-date":[95],"techniques":[97],"while":[98,145],"exposing":[99],"flexible":[100],"interfaces":[101],"request":[103],"routing,":[104],"cache":[105],"management,":[106],"scheduling":[108],"policies.":[109],"In":[110],"TPU":[112],"case":[113],"study,":[114],"our":[115],"profiler":[116],"requires":[117],"18.5\u00d7":[118],"fewer":[119],"LoC":[120],"outperforms":[122],"predecessor's":[124],"hardware-simulator":[125],"integration,":[126],"demonstrating":[127],"LLMServingSim2.0's":[128],"low-effort":[129],"extensibility.":[131],"Our":[132],"experiments":[133],"show":[135],"reproduces":[138],"GPU-based":[139],"1.9%":[143],"error,":[144],"maintaining":[146],"practical":[147],"simulation":[148],"time,":[149],"making":[150],"it":[151],"comprehensive":[153],"platform":[154],"both":[156],"developers":[158],"service":[161],"providers.":[162]},"counts_by_year":[],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-11-03T00:00:00"}
