{"id":"https://openalex.org/W7162438239","doi":"https://doi.org/10.1145/3801489.3806912","title":"WISP: Waste- and Interference-Suppressed Distributed Speculative LLM Serving at the Edge via Dynamic Drafting and SLO-Aware Batching","display_name":"WISP: Waste- and Interference-Suppressed Distributed Speculative LLM Serving at the Edge via Dynamic Drafting and SLO-Aware Batching","publication_year":2026,"publication_date":"2026-05-26","ids":{"openalex":"https://openalex.org/W7162438239","doi":"https://doi.org/10.1145/3801489.3806912"},"language":null,"primary_location":{"id":"doi:10.1145/3801489.3806912","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3801489.3806912","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":"Abstracts of the 2026 ACM SIGMETRICS International Conference on Measurement and Modeling of Computer Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3801489.3806912","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137014809","display_name":"Xiangchen Li","orcid":"https://orcid.org/0000-0002-5293-5348"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiangchen Li","raw_affiliation_strings":["Virginia Tech, Blacksburg, Virginia, USA"],"raw_orcid":"https://orcid.org/0000-0002-5293-5348","affiliations":[{"raw_affiliation_string":"Virginia Tech, Blacksburg, Virginia, USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125658018","display_name":"Jiakun Fan","orcid":null},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiakun Fan","raw_affiliation_strings":["Virginia Tech, Blacksburg, Virginia, USA"],"raw_orcid":"https://orcid.org/0009-0004-4563-8697","affiliations":[{"raw_affiliation_string":"Virginia Tech, Blacksburg, Virginia, USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062719337","display_name":"Qingyuan Wang","orcid":"https://orcid.org/0000-0002-7879-4328"},"institutions":[{"id":"https://openalex.org/I100930933","display_name":"University College Dublin","ror":"https://ror.org/05m7pjf47","country_code":"IE","type":"education","lineage":["https://openalex.org/I100930933"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Qingyuan Wang","raw_affiliation_strings":["University College Dublin, Dublin, Ireland"],"raw_orcid":"https://orcid.org/0000-0002-7879-4328","affiliations":[{"raw_affiliation_string":"University College Dublin, Dublin, Ireland","institution_ids":["https://openalex.org/I100930933"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005011713","display_name":"Dimitrios Spatharakis","orcid":"https://orcid.org/0000-0002-0157-7173"},"institutions":[{"id":"https://openalex.org/I174458059","display_name":"National Technical University of Athens","ror":"https://ror.org/03cx6bg69","country_code":"GR","type":"education","lineage":["https://openalex.org/I174458059"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Dimitrios Spatharakis","raw_affiliation_strings":["National Technical University of Athens, Athens, Greece"],"raw_orcid":"https://orcid.org/0000-0002-0157-7173","affiliations":[{"raw_affiliation_string":"National Technical University of Athens, Athens, Greece","institution_ids":["https://openalex.org/I174458059"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019689955","display_name":"Saeid Ghafouri","orcid":"https://orcid.org/0000-0003-3799-5702"},"institutions":[{"id":"https://openalex.org/I126231945","display_name":"Queen's University Belfast","ror":"https://ror.org/00hswnk62","country_code":"GB","type":"education","lineage":["https://openalex.org/I126231945"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Saeid Ghafouri","raw_affiliation_strings":["Queen's University Belfast, Belfast, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0003-3799-5702","affiliations":[{"raw_affiliation_string":"Queen's University Belfast, Belfast, United Kingdom","institution_ids":["https://openalex.org/I126231945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086758775","display_name":"Hans Vandierendonck","orcid":"https://orcid.org/0000-0001-5868-9259"},"institutions":[{"id":"https://openalex.org/I126231945","display_name":"Queen's University Belfast","ror":"https://ror.org/00hswnk62","country_code":"GB","type":"education","lineage":["https://openalex.org/I126231945"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Hans Vandierendonck","raw_affiliation_strings":["Queens University Belfast, Belfast, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0001-5868-9259","affiliations":[{"raw_affiliation_string":"Queens University Belfast, Belfast, United Kingdom","institution_ids":["https://openalex.org/I126231945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029098934","display_name":"Deepu John","orcid":"https://orcid.org/0000-0002-6139-1100"},"institutions":[{"id":"https://openalex.org/I100930933","display_name":"University College Dublin","ror":"https://ror.org/05m7pjf47","country_code":"IE","type":"education","lineage":["https://openalex.org/I100930933"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Deepu John","raw_affiliation_strings":["University College Dublin, Dublin, Ireland"],"raw_orcid":"https://orcid.org/0000-0002-6139-1100","affiliations":[{"raw_affiliation_string":"University College Dublin, Dublin, Ireland","institution_ids":["https://openalex.org/I100930933"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137037694","display_name":"Bo Ji","orcid":"https://orcid.org/0000-0003-0149-7509"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bo Ji","raw_affiliation_strings":["Virginia Tech, Blacksburg, Virginia, USA"],"raw_orcid":"https://orcid.org/0000-0003-0149-7509","affiliations":[{"raw_affiliation_string":"Virginia Tech, Blacksburg, Virginia, USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137026970","display_name":"Ali R. Butt","orcid":"https://orcid.org/0000-0002-0871-7263"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ali R. Butt","raw_affiliation_strings":["Virginia Tech, Blacksburg, Virginia, USA"],"raw_orcid":"https://orcid.org/0000-0002-0871-7263","affiliations":[{"raw_affiliation_string":"Virginia Tech, Blacksburg, Virginia, USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113899214","display_name":"Dimitrios Nikolopoulos","orcid":null},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dimitrios Nikolopoulos","raw_affiliation_strings":["Virginia Tech, Blacksburg, Virginia, USA"],"raw_orcid":"https://orcid.org/0000-0003-0217-8307","affiliations":[{"raw_affiliation_string":"Virginia Tech, Blacksburg, Virginia, USA","institution_ids":["https://openalex.org/I859038795"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":10,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.86542787,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"28","last_page":"30"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.4320000112056732,"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":0.4320000112056732,"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/T12127","display_name":"Software System Performance and Reliability","score":0.22200000286102295,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.07100000232458115,"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/goodput","display_name":"Goodput","score":0.8084999918937683},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.6639000177383423},{"id":"https://openalex.org/keywords/edge-device","display_name":"Edge device","score":0.46320000290870667},{"id":"https://openalex.org/keywords/lossless-compression","display_name":"Lossless compression","score":0.39660000801086426},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.39309999346733093},{"id":"https://openalex.org/keywords/edge-computing","display_name":"Edge computing","score":0.33739998936653137}],"concepts":[{"id":"https://openalex.org/C94022561","wikidata":"https://www.wikidata.org/wiki/Q1172393","display_name":"Goodput","level":4,"score":0.8084999918937683},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8062999844551086},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.6639000177383423},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.555400013923645},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.46320000290870667},{"id":"https://openalex.org/C81081738","wikidata":"https://www.wikidata.org/wiki/Q55542","display_name":"Lossless compression","level":3,"score":0.39660000801086426},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.39309999346733093},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3919999897480011},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.33739998936653137},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.32019999623298645},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.3138999938964844},{"id":"https://openalex.org/C162932704","wikidata":"https://www.wikidata.org/wiki/Q1058791","display_name":"Synchronizing","level":3,"score":0.29089999198913574},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.2754000127315521},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.26589998602867126},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.265500009059906}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3801489.3806912","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3801489.3806912","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":"Abstracts of the 2026 ACM SIGMETRICS International Conference on Measurement and Modeling of Computer Systems","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3801489.3806912","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3801489.3806912","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":"Abstracts of the 2026 ACM SIGMETRICS International Conference on Measurement and Modeling of Computer Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W4404134026","https://openalex.org/W4416955988"],"related_works":[],"abstract_inverted_index":{"LLM":[0],"inference":[1],"is":[2],"increasingly":[3],"initiated":[4],"at":[5],"edge":[6,17],"devices":[7,41],"but":[8],"still":[9],"executed":[10],"in":[11],"centralized":[12,105],"GPU":[13],"clusters.":[14],"Distributed":[15],"speculative":[16,67],"serving":[18,68,106],"offloads":[19],"drafting":[20,73],"to":[21,102,117],"devices,":[22],"yet":[23],"existing":[24],"systems":[25],"scale":[26],"poorly":[27],"under":[28,126],"heterogeneous,":[29],"latency-sensitive":[30],"workloads.":[31,129],"We":[32,61],"identify":[33],"two":[34],"bottlenecks:":[35],"Wasted":[36],"Drafting":[37],"Time":[38],"(WDT),":[39],"where":[40,52],"over-draft":[42],"tokens":[43],"later":[44],"rejected":[45],"by":[46,100,115],"the":[47],"verifier,":[48],"and":[49,87,93,107,111,119],"Verification":[50],"Interference,":[51],"long":[53],"verifications":[54],"delay":[55],"short":[56],"requests":[57],"within":[58],"a":[59,64,80,84],"micro-batch.":[60],"present":[62],"WISP,":[63],"lossless":[65],"distributed":[66],"system":[69,98,113],"that":[70],"combines":[71],"dynamic":[72],"with":[74],"SLO-aware":[75],"verification":[76],"batching.":[77],"WISP":[78,96],"uses":[79],"lightweight":[81],"rejection":[82],"predictor,":[83],"batch-latency":[85],"estimator,":[86],"an":[88],"interference-aware":[89],"scheduler.":[90],"Across":[91],"simulation":[92],"prototype":[94],"experiments,":[95],"improves":[97,112],"capacity":[99],"up":[101,116],"2.1\u00d7":[103],"over":[104,109],"4.1\u00d7":[108],"SLED,":[110],"goodput":[114],"1.94\u00d7":[118],"3.7\u00d7,":[120],"while":[121],"reducing":[122],"token-speed":[123],"SLO":[124],"violations":[125],"bursty":[127],"multi-tenant":[128]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-27T00:00:00"}
