{"id":"https://openalex.org/W4416004238","doi":"https://doi.org/10.1145/3731599.3767396","title":"WAGES: Workload-Aware GPU Sharing System for Energy-Efficient Serverless LLM Serving","display_name":"WAGES: Workload-Aware GPU Sharing System for Energy-Efficient Serverless LLM Serving","publication_year":2025,"publication_date":"2025-11-07","ids":{"openalex":"https://openalex.org/W4416004238","doi":"https://doi.org/10.1145/3731599.3767396"},"language":null,"primary_location":{"id":"doi:10.1145/3731599.3767396","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731599.3767396","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 SC '25 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3731599.3767396","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000573074","display_name":"Timothy R. W. Wang","orcid":"https://orcid.org/0009-0007-4777-8337"},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Tianyu Wang","raw_affiliation_strings":["University of Pittsburgh, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"University of Pittsburgh, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I170201317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026624531","display_name":"Gourav Rattihalli","orcid":"https://orcid.org/0000-0002-0373-1867"},"institutions":[{"id":"https://openalex.org/I4210122178","display_name":"Hewlett Packard Enterprise (United States)","ror":"https://ror.org/020x0c621","country_code":"US","type":"company","lineage":["https://openalex.org/I4210122178"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gourav Rattihalli","raw_affiliation_strings":["Hewlett Packard Enterprise (HPE), Milpitas, CA, USA"],"affiliations":[{"raw_affiliation_string":"Hewlett Packard Enterprise (HPE), Milpitas, CA, USA","institution_ids":["https://openalex.org/I4210122178"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077061884","display_name":"Aditya Dhakal","orcid":"https://orcid.org/0000-0002-8297-8525"},"institutions":[{"id":"https://openalex.org/I4210122178","display_name":"Hewlett Packard Enterprise (United States)","ror":"https://ror.org/020x0c621","country_code":"US","type":"company","lineage":["https://openalex.org/I4210122178"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aditya Dhakal","raw_affiliation_strings":["Hewlett Packard Enterprise (HPE), Milpitas, CA, USA"],"affiliations":[{"raw_affiliation_string":"Hewlett Packard Enterprise (HPE), Milpitas, CA, USA","institution_ids":["https://openalex.org/I4210122178"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087859795","display_name":"Xulong Tang","orcid":"https://orcid.org/0000-0002-3385-2053"},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xulong Tang","raw_affiliation_strings":["University of Pittsburgh, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"University of Pittsburgh, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I170201317"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027761275","display_name":"Dejan Miloji\u010di\u0107","orcid":"https://orcid.org/0000-0001-9830-8588"},"institutions":[{"id":"https://openalex.org/I4210122178","display_name":"Hewlett Packard Enterprise (United States)","ror":"https://ror.org/020x0c621","country_code":"US","type":"company","lineage":["https://openalex.org/I4210122178"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dejan Milojicic","raw_affiliation_strings":["Hewlett Packard Enterprise (HPE), Palo Alto, CA, USA"],"affiliations":[{"raw_affiliation_string":"Hewlett Packard Enterprise (HPE), Palo Alto, CA, USA","institution_ids":["https://openalex.org/I4210122178"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5000573074"],"corresponding_institution_ids":["https://openalex.org/I170201317"],"apc_list":null,"apc_paid":null,"fwci":3.6264,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.94911089,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"508","last_page":"515"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.5067999958992004,"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"}},"topics":[{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.5067999958992004,"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":0.15610000491142273,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.14100000262260437,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/provisioning","display_name":"Provisioning","score":0.5393000245094299},{"id":"https://openalex.org/keywords/multiplexing","display_name":"Multiplexing","score":0.49059998989105225},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.48980000615119934},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.39579999446868896},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.3743000030517578},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3181000053882599}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8133999705314636},{"id":"https://openalex.org/C172191483","wikidata":"https://www.wikidata.org/wiki/Q1071806","display_name":"Provisioning","level":2,"score":0.5393000245094299},{"id":"https://openalex.org/C19275194","wikidata":"https://www.wikidata.org/wiki/Q222903","display_name":"Multiplexing","level":2,"score":0.49059998989105225},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.48980000615119934},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.4140999913215637},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.39579999446868896},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3846000134944916},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.3743000030517578},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.34279999136924744},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3181000053882599},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.3174999952316284},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.314300000667572},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.3086000084877014},{"id":"https://openalex.org/C178693496","wikidata":"https://www.wikidata.org/wiki/Q911691","display_name":"Clock rate","level":3,"score":0.2992999851703644},{"id":"https://openalex.org/C50661577","wikidata":"https://www.wikidata.org/wiki/Q901831","display_name":"Time-division multiplexing","level":3,"score":0.2793999910354614},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.2728999853134155},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.267300009727478},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.26269999146461487},{"id":"https://openalex.org/C2779965156","wikidata":"https://www.wikidata.org/wiki/Q5227350","display_name":"Data sharing","level":3,"score":0.260699987411499},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.25690001249313354}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3731599.3767396","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731599.3767396","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 SC '25 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3731599.3767396","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731599.3767396","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 SC '25 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2971317361","https://openalex.org/W3097411828","https://openalex.org/W4214690606","https://openalex.org/W4293025059","https://openalex.org/W4304192541","https://openalex.org/W4387005975","https://openalex.org/W4387321091","https://openalex.org/W4388041447","https://openalex.org/W4388581250","https://openalex.org/W4394923129","https://openalex.org/W4404954484","https://openalex.org/W4405756372","https://openalex.org/W4407218922","https://openalex.org/W4408049809","https://openalex.org/W4408867174","https://openalex.org/W4408867487","https://openalex.org/W4409248734"],"related_works":[],"abstract_inverted_index":{"Serverless":[0],"LLM":[1,57],"serving":[2],"reduces":[3],"operational":[4],"costs":[5],"by":[6],"elastically":[7],"provisioning":[8],"GPUs":[9],"and":[10,39,43,66,75],"charging":[11],"users":[12],"only":[13],"for":[14,72],"actual":[15],"usage.":[16],"However,":[17],"existing":[18],"systems":[19],"mainly":[20],"optimize":[21],"cold-start":[22],"latency":[23],"while":[24],"overlooking":[25],"two":[26],"inefficiencies:":[27],"(i)":[28],"static,":[29],"exclusive":[30],"GPU":[31,73],"allocation":[32],"that":[33,55],"over-provisions":[34],"compute":[35],"resources,":[36],"lowering":[37],"utilization":[38],"inflating":[40],"hardware":[41],"costs,":[42],"(ii)":[44],"reliance":[45],"on":[46],"hardware-controlled":[47],"clock":[48,68,77],"frequencies,":[49],"wasting":[50],"energy.":[51],"Our":[52],"measurements":[53],"show":[54],"many":[56],"workloads":[58],"can":[59],"meet":[60],"SLOs":[61],"with":[62],"partial":[63],"SM":[64],"allocations":[65],"reduced":[67],"speeds,":[69],"enabling":[70],"opportunities":[71],"multiplexing":[74],"dynamic":[76],"scaling":[78],"to":[79],"reduce":[80],"energy":[81],"consumption.":[82]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-07T00:00:00"}