{"id":"https://openalex.org/W4411486143","doi":"https://doi.org/10.1145/3695053.3731093","title":"RAGO: Systematic Performance Optimization for Retrieval-Augmented Generation Serving","display_name":"RAGO: Systematic Performance Optimization for Retrieval-Augmented Generation Serving","publication_year":2025,"publication_date":"2025-06-20","ids":{"openalex":"https://openalex.org/W4411486143","doi":"https://doi.org/10.1145/3695053.3731093"},"language":"en","primary_location":{"id":"doi:10.1145/3695053.3731093","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3695053.3731093","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3695053.3731093","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 52nd Annual International Symposium on Computer Architecture","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3695053.3731093","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031344912","display_name":"Wenqi Jiang","orcid":"https://orcid.org/0000-0003-3895-7943"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Wenqi Jiang","raw_affiliation_strings":["ETH Zurich, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0003-3895-7943","affiliations":[{"raw_affiliation_string":"ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103255393","display_name":"Suvinay Subramanian","orcid":"https://orcid.org/0000-0002-8715-8964"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Suvinay Subramanian","raw_affiliation_strings":["Google, Mountain View, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-8715-8964","affiliations":[{"raw_affiliation_string":"Google, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003376752","display_name":"Catherine E. Graves","orcid":"https://orcid.org/0000-0002-0907-583X"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cat Graves","raw_affiliation_strings":["Google DeepMind, Mountain View, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-0907-583X","affiliations":[{"raw_affiliation_string":"Google DeepMind, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103144919","display_name":"Gustavo Alonso","orcid":"https://orcid.org/0000-0002-4396-6695"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Gustavo Alonso","raw_affiliation_strings":["ETH Zurich, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-4396-6695","affiliations":[{"raw_affiliation_string":"ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070172290","display_name":"Amir Yazdanbakhsh","orcid":"https://orcid.org/0000-0001-8199-7671"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amir Yazdanbakhsh","raw_affiliation_strings":["Google DeepMind, Mountain View, CA, USA"],"raw_orcid":"https://orcid.org/0000-0001-8199-7671","affiliations":[{"raw_affiliation_string":"Google DeepMind, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063419167","display_name":"Vidushi Dadu","orcid":"https://orcid.org/0000-0003-1654-6684"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vidushi Dadu","raw_affiliation_strings":["Google, Sunnyvale, USA"],"raw_orcid":"https://orcid.org/0000-0003-1654-6684","affiliations":[{"raw_affiliation_string":"Google, Sunnyvale, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"974","last_page":"989"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9887999892234802,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9887999892234802,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.984499990940094,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10203","display_name":"Recommender Systems and Techniques","score":0.980400025844574,"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/computer-science","display_name":"Computer science","score":0.737680196762085},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4085083305835724}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.737680196762085},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4085083305835724}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3695053.3731093","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3695053.3731093","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3695053.3731093","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 52nd Annual International Symposium on Computer Architecture","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3695053.3731093","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3695053.3731093","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3695053.3731093","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 52nd Annual International Symposium on Computer Architecture","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320317153","display_name":"DeepMind","ror":"https://ror.org/00971b260"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411486143.pdf","grobid_xml":"https://content.openalex.org/works/W4411486143.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W4258001","https://openalex.org/W2086179657","https://openalex.org/W2124592110","https://openalex.org/W2130821339","https://openalex.org/W2151697120","https://openalex.org/W2210781143","https://openalex.org/W2512971201","https://openalex.org/W2782800349","https://openalex.org/W2940862705","https://openalex.org/W2963323070","https://openalex.org/W2963339397","https://openalex.org/W2969388332","https://openalex.org/W2970641574","https://openalex.org/W2970771982","https://openalex.org/W2979937837","https://openalex.org/W2980104813","https://openalex.org/W2992678377","https://openalex.org/W3028864969","https://openalex.org/W3085011441","https://openalex.org/W3121313599","https://openalex.org/W3129831491","https://openalex.org/W3156789018","https://openalex.org/W3166863226","https://openalex.org/W4213249026","https://openalex.org/W4280568654","https://openalex.org/W4287887100","https://openalex.org/W4318464200","https://openalex.org/W4381329135","https://openalex.org/W4381610063","https://openalex.org/W4384561707","https://openalex.org/W4387321071","https://openalex.org/W4387321091","https://openalex.org/W4388031336","https://openalex.org/W4388778348","https://openalex.org/W4389491850","https://openalex.org/W4389519118","https://openalex.org/W4401211590","https://openalex.org/W4401211807","https://openalex.org/W4407355496"],"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":{"Retrieval-augmented":[0],"generation":[1],"(RAG)":[2],"is":[3],"emerging":[4],"as":[5,62],"a":[6,50,63,99,110,117],"popular":[7],"approach":[8],"for":[9,65,103],"reliable":[10],"LLM":[11],"serving.However,":[12],"efficient":[13,104],"RAG":[14,27,45,59,72,105,125],"serving":[15,61],"remains":[16],"an":[17],"open":[18],"challenge":[19],"due":[20],"to":[21,43,84,109,124],"the":[22,30,55],"rapid":[23],"emergence":[24],"of":[25,58],"many":[26],"variants":[28],"and":[29,88,116],"substantial":[31],"differences":[32],"in":[33,112,120],"workload":[34],"characteristics":[35],"across":[36,81],"them.This":[37],"paper":[38],"makes":[39],"three":[40],"fundamental":[41],"contributions":[42],"advancing":[44],"serving.First,":[46],"we":[47,68,93],"introduce":[48],"RAGSchema,":[49,76],"structured":[51],"abstraction":[52],"that":[53],"captures":[54],"wide":[56],"range":[57],"algorithms,":[60],"foundation":[64],"performance":[66,79,91],"optimization.Second,":[67],"analyze":[69],"several":[70],"representative":[71],"workloads":[73],"with":[74],"distinct":[75],"revealing":[77],"significant":[78],"variability":[80,87],"these":[82],"workloads.Third,":[83],"address":[85],"this":[86],"meet":[89],"diverse":[90],"requirements,":[92],"propose":[94],"RAGO":[95],"(Retrieval-Augmented":[96],"Generation":[97],"Optimizer),":[98],"system":[100],"optimization":[101],"framework":[102],"serving.RAGO":[106],"achieves":[107],"up":[108],"2increase":[111],"QPS":[113],"per":[114],"chip":[115],"55%":[118],"reduction":[119],"time-to-first-token":[121],"latency":[122],"compared":[123],"systems":[126],"built":[127],"on":[128],"LLM-system":[129],"extensions.":[130]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}