{"id":"https://openalex.org/W7163561398","doi":"https://doi.org/10.23919/date69613.2026.11539301","title":"A Scheduling Framework for Efficient MoE Inference on Edge GPU-NDP Systems","display_name":"A Scheduling Framework for Efficient MoE Inference on Edge GPU-NDP Systems","publication_year":2026,"publication_date":"2026-04-20","ids":{"openalex":"https://openalex.org/W7163561398","doi":"https://doi.org/10.23919/date69613.2026.11539301"},"language":null,"primary_location":{"id":"doi:10.23919/date69613.2026.11539301","is_oa":false,"landing_page_url":"https://doi.org/10.23919/date69613.2026.11539301","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 Design, Automation & Test in Europe Conference (DATE)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2601.03992","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137844422","display_name":"Qi Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Wu","raw_affiliation_strings":["Nanjing University,School of Electronic Science and Engineering,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University,School of Electronic Science and Engineering,China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137849180","display_name":"Chao Fang","orcid":null},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Fang","raw_affiliation_strings":["Nanjing University,School of Electronic Science and Engineering,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University,School of Electronic Science and Engineering,China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031618552","display_name":"Jiayuan Chen","orcid":"https://orcid.org/0000-0002-2581-951X"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiayuan Chen","raw_affiliation_strings":["China Mobile Research Institute,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Mobile Research Institute,China","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103326664","display_name":"Ye Lin","orcid":"https://orcid.org/0009-0000-5424-2265"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ye Lin","raw_affiliation_strings":["Nanjing University,School of Electronic Science and Engineering,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University,School of Electronic Science and Engineering,China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065445596","display_name":"Yu Zhang","orcid":"https://orcid.org/0000-0002-2358-0904"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yueqi Zhang","raw_affiliation_strings":["Nanjing University,School of Electronic Science and Engineering,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University,School of Electronic Science and Engineering,China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080870367","display_name":"Yichuan Bai","orcid":"https://orcid.org/0000-0001-8895-1780"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yichuan Bai","raw_affiliation_strings":["Nanjing University,School of Electronic Science and Engineering,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University,School of Electronic Science and Engineering,China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137860502","display_name":"Yuan Du","orcid":null},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan Du","raw_affiliation_strings":["Nanjing University,School of Electronic Science and Engineering,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University,School of Electronic Science and Engineering,China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5137860805","display_name":"Li Du","orcid":null},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Du","raw_affiliation_strings":["Nanjing University,School of Electronic Science and Engineering,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University,School of Electronic Science and Engineering,China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.16660000383853912,"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"}},"topics":[{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.16660000383853912,"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":0.1396999955177307,"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/T14347","display_name":"Big Data and Digital Economy","score":0.10209999978542328,"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/scheduling","display_name":"Scheduling (production processes)","score":0.5857999920845032},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4449000060558319},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.33079999685287476},{"id":"https://openalex.org/keywords/job-shop-scheduling","display_name":"Job shop scheduling","score":0.31839999556541443}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6521999835968018},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5857999920845032},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4449000060558319},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.399399995803833},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.36970001459121704},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.33079999685287476},{"id":"https://openalex.org/C55416958","wikidata":"https://www.wikidata.org/wiki/Q6206757","display_name":"Job shop scheduling","level":3,"score":0.31839999556541443},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2565999925136566},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2485000044107437},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2296999990940094}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.23919/date69613.2026.11539301","is_oa":false,"landing_page_url":"https://doi.org/10.23919/date69613.2026.11539301","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 Design, Automation & Test in Europe Conference (DATE)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2601.03992","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2601.03992","pdf_url":"https://arxiv.org/pdf/2601.03992","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2601.03992","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2601.03992","pdf_url":"https://arxiv.org/pdf/2601.03992","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334982","display_name":"Basic Research Program of Jiangsu Province","ror":null},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7163561398.pdf"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W2150884987","https://openalex.org/W2762749859","https://openalex.org/W2979719709","https://openalex.org/W2982008795","https://openalex.org/W3043023836","https://openalex.org/W4225739994","https://openalex.org/W4321636575","https://openalex.org/W4383749542","https://openalex.org/W4385245566","https://openalex.org/W4388757726","https://openalex.org/W4393141038","https://openalex.org/W4393406920","https://openalex.org/W4394998968","https://openalex.org/W4401211602","https://openalex.org/W4401568811","https://openalex.org/W4401568823","https://openalex.org/W4402671950","https://openalex.org/W4404955001","https://openalex.org/W4406892517","https://openalex.org/W4407197341","https://openalex.org/W4408858386","https://openalex.org/W4408894550","https://openalex.org/W4409248488","https://openalex.org/W4409248815","https://openalex.org/W4409282453","https://openalex.org/W4410583035","https://openalex.org/W4410583075","https://openalex.org/W4414197520","https://openalex.org/W4416429558"],"related_works":[],"abstract_inverted_index":{"Mixture-of-Experts":[0],"(MoE)":[1],"models":[2,39],"facilitate":[3],"edge":[4,125],"deployment":[5],"by":[6,80],"decoupling":[7],"model":[8],"capacity":[9],"from":[10],"active":[11],"computation,":[12],"yet":[13],"their":[14],"large":[15,116],"memory":[16],"footprint":[17],"drives":[18],"the":[19,103],"need":[20],"for":[21,85],"GPU":[22,66,140],"systems":[23,44,167],"with":[24],"near-data":[25],"processing":[26,34],"(NDP)":[27],"capabilities":[28],"that":[29,162],"offload":[30],"experts":[31,154],"to":[32,57,112,141,155,168,175,182],"dedicated":[33],"units.":[35],"However,":[36],"deploying":[37],"MoE":[38,108,187],"on":[40,171],"such":[41],"edge-based":[42],"GPU-NDP":[43,166],"faces":[45],"three":[46,99],"critical":[47],"challenges:":[48],"1)":[49],"severe":[50],"load":[51],"imbalance":[52],"across":[53,119,136],"NDP":[54,72,121,137],"units":[55,122,138],"due":[56],"non-uniform":[58],"expert":[59,62,69,82,117,134],"selection":[60],"and":[61,74,114,139,173],"parallelism,":[63],"2)":[64],"insufficient":[65],"utilization":[67],"during":[68],"computation":[70],"within":[71],"units,":[73],"3)":[75],"extensive":[76],"data":[77],"pre-profiling":[78],"necessitated":[79],"unpredictable":[81],"activation":[83,157],"patterns":[84],"pre-fetching.":[86],"To":[87],"address":[88],"these":[89],"challenges,":[90],"this":[91],"paper":[92],"proposes":[93],"an":[94],"efficient":[95],"inference":[96,109,188],"framework":[97,164],"featuring":[98],"key":[100],"optimizations.":[101],"First,":[102],"underexplored":[104],"tensor":[105],"parallelism":[106],"in":[107,178,190],"is":[110],"exploited":[111],"partition":[113],"compute":[115],"parameters":[118],"multiple":[120],"simultaneously":[123],"towards":[124],"low-batch":[126],"scenarios.":[127],"Second,":[128],"a":[129,146],"load-balancing-aware":[130],"scheduling":[131],"algorithm":[132],"distributes":[133],"computations":[135],"maximize":[142],"resource":[143],"utilization.":[144],"Third,":[145],"dataset-free":[147],"pre-fetching":[148],"strategy":[149],"proactively":[150],"loads":[151],"frequently":[152],"accessed":[153],"minimize":[156],"delays.":[158],"Experimental":[159],"results":[160],"show":[161],"our":[163],"enables":[165],"achieve":[169],"2.41\u00d7":[170],"average":[172],"up":[174],"2.56\u00d7":[176],"speedup":[177],"end-to-end":[179],"latency":[180],"compared":[181],"state-of-the-art":[183],"approaches,":[184],"significantly":[185],"enhancing":[186],"efficiency":[189],"resource-constrained":[191],"environments.":[192]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-06-05T00:00:00"}