{"id":"https://openalex.org/W7110823685","doi":"https://doi.org/10.1145/3774899.3775017","title":"Illuminating the Hidden Challenges of Serverless LLM Systems","display_name":"Illuminating the Hidden Challenges of Serverless LLM Systems","publication_year":2025,"publication_date":"2025-12-09","ids":{"openalex":"https://openalex.org/W7110823685","doi":"https://doi.org/10.1145/3774899.3775017"},"language":null,"primary_location":{"id":"doi:10.1145/3774899.3775017","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774899.3775017","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th International Workshop on Serverless Computing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3774899.3775017","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Amit Samanta","orcid":"https://orcid.org/0000-0001-8854-048X"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Amit Samanta","raw_affiliation_strings":["University of Utah, Salt Lake City, UT, USA"],"raw_orcid":"https://orcid.org/0000-0001-8854-048X","affiliations":[{"raw_affiliation_string":"University of Utah, Salt Lake City, UT, USA","institution_ids":["https://openalex.org/I223532165"]}]},{"author_position":"last","author":{"id":null,"display_name":"Tri Gia Nguyen","orcid":"https://orcid.org/0000-0003-4578-9925"},"institutions":[{"id":"https://openalex.org/I109689652","display_name":"FPT University","ror":"https://ror.org/03esj4g97","country_code":"VN","type":"education","lineage":["https://openalex.org/I109689652"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Tri Gia Nguyen","raw_affiliation_strings":["FPT University, Da Nang, Vietnam"],"raw_orcid":"https://orcid.org/0000-0003-4578-9925","affiliations":[{"raw_affiliation_string":"FPT University, Da Nang, Vietnam","institution_ids":["https://openalex.org/I109689652"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I223532165"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.59992778,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"51","last_page":"57"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.36719998717308044,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.36719998717308044,"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/T14347","display_name":"Big Data and Digital Economy","score":0.09179999679327011,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.08550000190734863,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/stateful-firewall","display_name":"Stateful firewall","score":0.5935999751091003},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.578000009059906},{"id":"https://openalex.org/keywords/orchestration","display_name":"Orchestration","score":0.49140000343322754},{"id":"https://openalex.org/keywords/isolation","display_name":"Isolation (microbiology)","score":0.4275999963283539},{"id":"https://openalex.org/keywords/drone","display_name":"Drone","score":0.41100001335144043},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4068000018596649},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.38589999079704285}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7333999872207642},{"id":"https://openalex.org/C22927095","wikidata":"https://www.wikidata.org/wiki/Q1784206","display_name":"Stateful firewall","level":3,"score":0.5935999751091003},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.578000009059906},{"id":"https://openalex.org/C199168358","wikidata":"https://www.wikidata.org/wiki/Q3367000","display_name":"Orchestration","level":3,"score":0.49140000343322754},{"id":"https://openalex.org/C2775941552","wikidata":"https://www.wikidata.org/wiki/Q25212305","display_name":"Isolation (microbiology)","level":2,"score":0.4275999963283539},{"id":"https://openalex.org/C59519942","wikidata":"https://www.wikidata.org/wiki/Q650665","display_name":"Drone","level":2,"score":0.41100001335144043},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4068000018596649},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.38589999079704285},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.36579999327659607},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3418999910354614},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.3248000144958496},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.3043000102043152},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.28949999809265137},{"id":"https://openalex.org/C76947770","wikidata":"https://www.wikidata.org/wiki/Q4533181","display_name":"Ephemeral key","level":2,"score":0.2768999934196472},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.2678999900817871},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.26350000500679016},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.2574999928474426},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2554999887943268},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.2529999911785126}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3774899.3775017","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774899.3775017","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th International Workshop on Serverless Computing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3774899.3775017","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774899.3775017","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th International Workshop on Serverless Computing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W2774761221","https://openalex.org/W2997561286","https://openalex.org/W3112094022","https://openalex.org/W4214690606","https://openalex.org/W4214764640","https://openalex.org/W4404400601","https://openalex.org/W4404755868"],"related_works":[],"abstract_inverted_index":{"The":[0],"convergence":[1],"of":[2,45,64,100,121],"large":[3],"language":[4],"models":[5],"(LLMs)":[6],"and":[7,40,68,89,108,138],"serverless":[8,38,56,65,92,122,141],"computing":[9],"presents":[10],"a":[11,51,78,82,127],"unique":[12,62,98],"opportunity":[13],"to":[14,116,132],"make":[15,133],"cutting-edge":[16],"artificial":[17],"intelligence":[18],"(AI)":[19],"capabilities":[20],"more":[21,135],"widely":[22],"available.":[23],"However,":[24],"this":[25],"integration":[26],"provides":[27,126],"several":[28],"challenges":[29,99],"stemming":[30],"from":[31],"the":[32,41,61,97,118],"architectural":[33],"mismatch":[34],"between":[35],"stateless,":[36],"ephemeral":[37],"functions":[39],"resource-intensive,":[42],"stateful":[43],"nature":[44],"modern":[46],"LLMs.":[47,123],"This":[48,94,124],"paper":[49,95],"introduces":[50],"comprehensive":[52],"vision":[53],"for":[54,130],"efficient":[55,91],"LLM":[57,66],"systems.":[58],"We":[59],"analyze":[60],"requirements":[63],"systems":[67],"identify":[69],"gaps":[70],"in":[71],"existing":[72],"approaches.":[73],"Followed":[74],"by,":[75],"we":[76],"propose":[77],"three-layer":[79],"architecture":[80],"comprising":[81],"declarative":[83],"interface,":[84],"an":[85,90],"adaptive":[86],"orchestration":[87],"engine,":[88],"runtime.":[93],"highlights":[96],"cold":[101],"start":[102],"latency,":[103],"state":[104],"management,":[105],"resource":[106],"provisioning,":[107],"performance":[109],"isolation":[110],"that":[111],"must":[112],"be":[113],"dealt":[114],"with":[115],"understand":[117],"full":[119],"potential":[120],"work":[125],"foundational":[128],"roadmap":[129],"researchers":[131],"LLMs":[134],"accessible,":[136],"cost-effective,":[137],"scalable":[139],"through":[140],"paradigms.":[142]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-12-10T00:00:00"}
