{"id":"https://openalex.org/W7133227954","doi":"https://doi.org/10.1145/3789514.3796244","title":"Poster: Distributed Pipelined Collaborative Inference for LLMs on Edge Device Clusters","display_name":"Poster: Distributed Pipelined Collaborative Inference for LLMs on Edge Device Clusters","publication_year":2026,"publication_date":"2026-02-25","ids":{"openalex":"https://openalex.org/W7133227954","doi":"https://doi.org/10.1145/3789514.3796244"},"language":null,"primary_location":{"id":"doi:10.1145/3789514.3796244","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3789514.3796244","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 27th International Workshop on Mobile Computing Systems and Applications","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3789514.3796244","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046318408","display_name":"Hansong Zhou","orcid":"https://orcid.org/0000-0002-0423-9604"},"institutions":[{"id":"https://openalex.org/I103163165","display_name":"Florida State University","ror":"https://ror.org/05g3dte14","country_code":"US","type":"education","lineage":["https://openalex.org/I103163165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hansong Zhou","raw_affiliation_strings":["Computer Science, Florida State University, Tallahassee, USA"],"raw_orcid":"https://orcid.org/0000-0002-0423-9604","affiliations":[{"raw_affiliation_string":"Computer Science, Florida State University, Tallahassee, USA","institution_ids":["https://openalex.org/I103163165"]}]},{"author_position":"last","author":{"id":null,"display_name":"Xiaonan Zhang","orcid":"https://orcid.org/0000-0002-5913-6987"},"institutions":[{"id":"https://openalex.org/I103163165","display_name":"Florida State University","ror":"https://ror.org/05g3dte14","country_code":"US","type":"education","lineage":["https://openalex.org/I103163165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaonan Zhang","raw_affiliation_strings":["Computer Science, Florida State University, Tallahassee, USA"],"raw_orcid":"https://orcid.org/0000-0002-5913-6987","affiliations":[{"raw_affiliation_string":"Computer Science, Florida State University, Tallahassee, USA","institution_ids":["https://openalex.org/I103163165"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.27094628,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"158","last_page":"158"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.23669999837875366,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.23669999837875366,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.13590000569820404,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.05609999969601631,"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/cache","display_name":"Cache","score":0.6068000197410583},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.5843999981880188},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5760999917984009},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.48890000581741333},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.48840001225471497},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4659000039100647},{"id":"https://openalex.org/keywords/edge-computing","display_name":"Edge computing","score":0.46230000257492065},{"id":"https://openalex.org/keywords/edge-device","display_name":"Edge device","score":0.39309999346733093},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.3871999979019165}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8165000081062317},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.6068000197410583},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.5843999981880188},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5760999917984009},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.48890000581741333},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.48840001225471497},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.47530001401901245},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4659000039100647},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.46230000257492065},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.43050000071525574},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.39309999346733093},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.3871999979019165},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.36959999799728394},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.36239999532699585},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.3564000129699707},{"id":"https://openalex.org/C16320812","wikidata":"https://www.wikidata.org/wiki/Q1812200","display_name":"Idle","level":2,"score":0.34700000286102295},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.33980000019073486},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.3237999975681305},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.3124000132083893},{"id":"https://openalex.org/C38556500","wikidata":"https://www.wikidata.org/wiki/Q13404475","display_name":"Cache algorithms","level":4,"score":0.31060001254081726},{"id":"https://openalex.org/C70388272","wikidata":"https://www.wikidata.org/wiki/Q5968558","display_name":"IBM","level":2,"score":0.3095000088214874},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3043000102043152},{"id":"https://openalex.org/C165005293","wikidata":"https://www.wikidata.org/wiki/Q1074500","display_name":"Chip","level":2,"score":0.29260000586509705},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.2759999930858612},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.27480000257492065},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.2669000029563904},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.26330000162124634},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.26159998774528503}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3789514.3796244","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3789514.3796244","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 27th International Workshop on Mobile Computing Systems and Applications","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3789514.3796244","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3789514.3796244","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 27th International Workshop on Mobile Computing Systems and Applications","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G682165031","display_name":null,"funder_award_id":"CNS-2431553","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7559127633","display_name":null,"funder_award_id":"CCF-2312617","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8835374103","display_name":null,"funder_award_id":"CNS-2431439","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"Large":[1],"language":[2],"models":[3],"(LLMs)-based":[4],"intelligent":[5],"applications":[6],"are":[7],"increasingly":[8],"executed":[9],"on":[10],"user-owned":[11],"edge":[12,36],"devices":[13,21,91],"such":[14],"as":[15],"phones,":[16],"gateways,":[17],"and":[18,43],"smart":[19],"embedding":[20],"[2].":[22],"A":[23],"key":[24],"challenge":[25],"for":[26],"efficient":[27],"on-device":[28],"LLM":[29],"is":[30,105],"the":[31,60],"memory":[32],"wall.":[33],"On":[34],"resource-limited":[35],"devices,":[37],"model":[38],"with":[39],"billions":[40],"of":[41,59,80,88],"parameters":[42],"scaling":[44],"KV":[45],"cache":[46],"often":[47],"cannot":[48],"remain":[49],"resident":[50],"in":[51],"fast":[52],"device":[53],"memory.":[54],"Existing":[55],"solutions":[56],"migrate":[57],"part":[58],"burden":[61],"from":[62],"GPU":[63],"to":[64,77,96,108],"CPU,":[65],"but":[66],"this":[67,98,109],"usually":[68],"inflates":[69],"per-token":[70],"latency":[71],"during":[72],"auto-regressive":[73],"decoding":[74],"stage":[75],"due":[76],"repeated":[78],"movement":[79],"CPU-GPU":[81],"transfers.":[82],"Collaborative":[83],"inference":[84],"across":[85],"a":[86,93],"group":[87],"nearby":[89],"idle":[90],"offers":[92],"direct":[94],"way":[95],"break":[97],"constraint.":[99],"However,":[100],"conventional":[101],"tensor":[102],"parallelism":[103],"[1]":[104],"poorly":[106],"suited":[107],"case":[110],"since":[111],"its":[112],"frequent":[113],"all-reduce":[114],"collectives":[115],"introduces":[116],"significant":[117],"latency.":[118]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-03T00:00:00"}