{"id":"https://openalex.org/W7224437933","doi":"https://doi.org/10.18653/2026.emnlp-industry.64","title":"OpenDC-Infer-LC: Benchmarking Production-Valid Long-Context and RAG LLM Serving","display_name":"OpenDC-Infer-LC: Benchmarking Production-Valid Long-Context and RAG LLM Serving","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7224437933","doi":"https://doi.org/10.18653/2026.emnlp-industry.64"},"language":"en","primary_location":{"id":"doi:10.18653/2026.emnlp-industry.64","doi":"https://doi.org/10.18653/2026.emnlp-industry.64","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-industry.64","pdf_url":"https://aclanthology.org/2026.emnlp-industry.64.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://aclanthology.org/2026.emnlp-industry.64.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5160078272","display_name":"Yue Yang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yue Yang","raw_affiliation_strings":["Maincode , Melbourne , Australia,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Maincode , Melbourne , Australia,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137616988","display_name":"Maxwell Twelftree","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maxwell Twelftree","raw_affiliation_strings":["Maincode , Melbourne , Australia,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Maincode , Melbourne , Australia,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058072702","display_name":"Jared Collette","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jared Collette","raw_affiliation_strings":["Maincode , Melbourne , Australia,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Maincode , Melbourne , Australia,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160111317","display_name":"An-Chi He","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"An-Chi He","raw_affiliation_strings":["Maincode , Melbourne , Australia,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Maincode , Melbourne , Australia,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043675786","display_name":"Luke Borgnolo","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luke Borgnolo","raw_affiliation_strings":["Maincode , Melbourne , Australia,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Maincode , Melbourne , Australia,","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5140164502","display_name":"David Lemphers","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"David Lemphers","raw_affiliation_strings":["Maincode , Melbourne , Australia,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Maincode , Melbourne , Australia,","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.76192248,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1070","last_page":"1090"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.30880001187324524,"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":0.30880001187324524,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.2727000117301941,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.09350000321865082,"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/long-context-inference","display_name":"long-context inference","score":0.9539999961853027},{"id":"https://openalex.org/keywords/retrieval-augmented-generation","display_name":"retrieval-augmented generation","score":0.8700000047683716},{"id":"https://openalex.org/keywords/throughput","display_name":"throughput","score":0.3709999918937683},{"id":"https://openalex.org/keywords/routing","display_name":"routing","score":0.5730000138282776},{"id":"https://openalex.org/keywords/cache-reuse","display_name":"cache reuse","score":0.6430000066757202},{"id":"https://openalex.org/keywords/quantization","display_name":"quantization","score":0.7089999914169312}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.5740000009536743},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4634999930858612},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.2791000008583069},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.2605000138282776},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2597000002861023},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2535000145435333},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.251800000667572},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.23749999701976776},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.22429999709129333},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.21359999477863312}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/2026.emnlp-industry.64","doi":"https://doi.org/10.18653/2026.emnlp-industry.64","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-industry.64","pdf_url":"https://aclanthology.org/2026.emnlp-industry.64.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/2026.emnlp-industry.64","doi":"https://doi.org/10.18653/2026.emnlp-industry.64","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-industry.64","pdf_url":"https://aclanthology.org/2026.emnlp-industry.64.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7224437933.pdf","grobid_xml":"https://content.openalex.org/works/W7224437933.grobid-xml"},"referenced_works_count":3,"referenced_works":["https://openalex.org/W4393942918","https://openalex.org/W4394778349","https://openalex.org/W4402671766"],"related_works":["https://openalex.org/W4401043600","https://openalex.org/W6885056849","https://openalex.org/W7166831124","https://openalex.org/W4416037357","https://openalex.org/W4404783788","https://openalex.org/W4404783613","https://openalex.org/W4412889578","https://openalex.org/W4416034946","https://openalex.org/W4404781754","https://openalex.org/W7214940855"],"abstract_inverted_index":{"Long-context":[0],"and":[1,10,24,42,67,71,80,98,109,127],"RAG":[2,70],"workloads":[3],"expose":[4],"production":[5],"bottlenecks":[6],"that":[7,113],"raw":[8],"tokens/s":[9],"offline":[11],"accuracy":[12],"do":[13],"not":[14],"capture,":[15],"including":[16],"prefill":[17],"cost,":[18],"KV-cache":[19],"pressure,":[20],"prefix":[21],"reuse,":[22,122],"routing,":[23,125],"latency":[25],"SLOs.We":[26],"introduce":[27],"OpenDC-Infer-LC,":[28],"a":[29,85,90],"hardware-and":[30],"backendneutral":[31],"benchmark":[32,45],"for":[33,94],"evaluating":[34],"complete":[35],"data-center":[36],"LLM":[37],"serving":[38],"stacks":[39],"under":[40],"longcontext":[41],"retrieved-context":[43],"workloads.The":[44],"ranks":[46],"systems":[47],"by":[48],"SLO-qualified,":[49],"quality-preserving":[50],"goodput:":[51],"valid":[52],"output-token":[53],"throughput":[54],"at":[55],"the":[56,95],"highest":[57],"load":[58],"satisfying":[59],"p95":[60,62,64],"TTFT,":[61],"TPOT,":[63],"end-to-end":[65],"latency,":[66],"success-rate":[68],"targets.Because":[69],"Long-Bench":[72],"quality":[73,87,103],"depends":[74,116],"on":[75,106,118],"model":[76,97],"ability,":[77],"retrieval":[78],"difficulty,":[79,82],"task":[81],"OpenDC-Infer-LC":[83],"uses":[84],"relative":[86],"guardrail":[88],"against":[89],"low-load":[91],"reference":[92],"run":[93],"same":[96],"workload,":[99],"while":[100],"reporting":[101],"absolute":[102],"separately.Pilot":[104],"results":[105],"AMD":[107],"MI355X":[108],"NVIDIA":[110],"B200":[111],"show":[112],"deployable":[114],"capacity":[115],"strongly":[117],"backend":[119],"scheduling,":[120],"cache":[121],"context":[123],"length,":[124],"quantization,":[126],"runtime":[128],"maturity.":[129]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-10-30T00:00:00"}