{"id":"https://openalex.org/W7130335064","doi":"https://doi.org/10.1109/tencon66050.2025.11375380","title":"Efficient Task Scheduling Algorithms for Decentralized Large Language Model Serving","display_name":"Efficient Task Scheduling Algorithms for Decentralized Large Language Model Serving","publication_year":2025,"publication_date":"2025-10-27","ids":{"openalex":"https://openalex.org/W7130335064","doi":"https://doi.org/10.1109/tencon66050.2025.11375380"},"language":null,"primary_location":{"id":"doi:10.1109/tencon66050.2025.11375380","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tencon66050.2025.11375380","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"TENCON 2025 - 2025 IEEE Region 10 Conference (TENCON)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126300267","display_name":"Sanjaya Kumar Panda","orcid":null},"institutions":[{"id":"https://openalex.org/I121750182","display_name":"National Institute of Technology Warangal","ror":"https://ror.org/017ebfz38","country_code":"IN","type":"education","lineage":["https://openalex.org/I121750182"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sanjaya Kumar Panda","raw_affiliation_strings":["National Institute of Technology Warangal,Department of Computer Science and Engineering,Warangal,India,506004"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Technology Warangal,Department of Computer Science and Engineering,Warangal,India,506004","institution_ids":["https://openalex.org/I121750182"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126326488","display_name":"Sankalp Dubey","orcid":null},"institutions":[{"id":"https://openalex.org/I121750182","display_name":"National Institute of Technology Warangal","ror":"https://ror.org/017ebfz38","country_code":"IN","type":"education","lineage":["https://openalex.org/I121750182"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sankalp Dubey","raw_affiliation_strings":["National Institute of Technology Warangal,Department of Computer Science and Engineering,Warangal,India,506004"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Technology Warangal,Department of Computer Science and Engineering,Warangal,India,506004","institution_ids":["https://openalex.org/I121750182"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051156102","display_name":"Siba Mishra","orcid":"https://orcid.org/0000-0002-9893-595X"},"institutions":[{"id":"https://openalex.org/I4210125057","display_name":"Vivekananda Global University","ror":"https://ror.org/038mz4r36","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210125057"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Siba Mishra","raw_affiliation_strings":["C. V. Raman Global University,Department of Computer Science and Engineering,Bhubaneswar,India,752054"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"C. V. Raman Global University,Department of Computer Science and Engineering,Bhubaneswar,India,752054","institution_ids":["https://openalex.org/I4210125057"]}]}],"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":0.69031382,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1023","last_page":"1027"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14347","display_name":"Big Data and Digital Economy","score":0.2639000117778778,"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/T14347","display_name":"Big Data and Digital Economy","score":0.2639000117778778,"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":0.09939999878406525,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.08940000087022781,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.6335999965667725},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5666999816894531},{"id":"https://openalex.org/keywords/greedy-algorithm","display_name":"Greedy algorithm","score":0.43939998745918274},{"id":"https://openalex.org/keywords/dynamic-priority-scheduling","display_name":"Dynamic priority scheduling","score":0.4343000054359436},{"id":"https://openalex.org/keywords/critical-path-method","display_name":"Critical path method","score":0.4250999987125397},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4163999855518341},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.41589999198913574},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.40700000524520874},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.3418000042438507}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8736000061035156},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.6335999965667725},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.6129999756813049},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5666999816894531},{"id":"https://openalex.org/C51823790","wikidata":"https://www.wikidata.org/wiki/Q504353","display_name":"Greedy algorithm","level":2,"score":0.43939998745918274},{"id":"https://openalex.org/C107568181","wikidata":"https://www.wikidata.org/wiki/Q5319000","display_name":"Dynamic priority scheduling","level":3,"score":0.4343000054359436},{"id":"https://openalex.org/C115874739","wikidata":"https://www.wikidata.org/wiki/Q825377","display_name":"Critical path method","level":2,"score":0.4250999987125397},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4163999855518341},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.41589999198913574},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.40700000524520874},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.34310001134872437},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3418000042438507},{"id":"https://openalex.org/C55416958","wikidata":"https://www.wikidata.org/wiki/Q6206757","display_name":"Job shop scheduling","level":3,"score":0.33059999346733093},{"id":"https://openalex.org/C122141398","wikidata":"https://www.wikidata.org/wiki/Q5456330","display_name":"Fixed-priority pre-emptive scheduling","level":5,"score":0.3151000142097473},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.30979999899864197},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.30799999833106995},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.3061999976634979},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.3034999966621399},{"id":"https://openalex.org/C31689143","wikidata":"https://www.wikidata.org/wiki/Q733809","display_name":"Fair-share scheduling","level":3,"score":0.2962999939918518},{"id":"https://openalex.org/C311688","wikidata":"https://www.wikidata.org/wiki/Q2393193","display_name":"Time complexity","level":2,"score":0.29589998722076416},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.28700000047683716},{"id":"https://openalex.org/C16320812","wikidata":"https://www.wikidata.org/wiki/Q1812200","display_name":"Idle","level":2,"score":0.2809000015258789},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.27950000762939453},{"id":"https://openalex.org/C127456818","wikidata":"https://www.wikidata.org/wiki/Q238879","display_name":"Rate-monotonic scheduling","level":4,"score":0.2669999897480011},{"id":"https://openalex.org/C162262903","wikidata":"https://www.wikidata.org/wiki/Q343527","display_name":"Allocator","level":2,"score":0.26669999957084656},{"id":"https://openalex.org/C114290370","wikidata":"https://www.wikidata.org/wiki/Q1415915","display_name":"Null-move heuristic","level":3,"score":0.26489999890327454},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.2628999948501587},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.26010000705718994},{"id":"https://openalex.org/C74197172","wikidata":"https://www.wikidata.org/wiki/Q1195339","display_name":"Directed acyclic graph","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C32310161","wikidata":"https://www.wikidata.org/wiki/Q666365","display_name":"Earliest deadline first scheduling","level":5,"score":0.2563000023365021}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tencon66050.2025.11375380","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tencon66050.2025.11375380","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"TENCON 2025 - 2025 IEEE Region 10 Conference (TENCON)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.6441907286643982}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2923014074","https://openalex.org/W4385597806","https://openalex.org/W4391136507","https://openalex.org/W4407881031","https://openalex.org/W4409282468","https://openalex.org/W4409796734"],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"(LLMs)":[3],"have":[4,50],"gained":[5],"enormous":[6],"popularity":[7],"for":[8,32,97,152],"processing":[9,28],"and":[10,115,144,172,178,186,206,221,223,228,233],"generating":[11,98],"text.":[12],"They":[13],"are":[14,124,183],"a":[15,41,164,167],"subset":[16],"of":[17,26,190,204],"generative":[18],"artificial":[19],"intelligence":[20],"(GenAI)":[21],"that":[22,214],"require":[23],"higher":[24],"availability":[25],"graphical":[27],"unit":[29],"(GPU)":[30],"resources":[31,38,95,123],"inference":[33,66,73,110],"services.":[34],"However,":[35],"making":[36],"GPU":[37,61,94,117,122,168],"available":[39],"in":[40,81,107,202],"centralized":[42],"infrastructure":[43,55],"is":[44,105],"quite":[45],"challenging.":[46],"Therefore,":[47],"recent":[48,192],"works":[49],"focused":[51],"on":[52],"decentralized":[53,70,108,153],"physical":[54],"networks":[56],"(DePIN)":[57],"to":[58,88,112,156,166,219,226,231],"utilize":[59],"idle":[60],"resources,":[62],"enabling":[63],"scalable":[64],"LLM":[65,109,154],"services":[67,74,111],"across":[68],"the":[69,136,145,191,195],"network.":[71],"These":[72],"may":[75],"experience":[76],"inherent":[77],"latency":[78],"(i.e.,":[79],"measured":[80],"time":[82,92,208],"per":[83],"output":[84],"token":[85],"(TPOT))":[86],"due":[87],"communication":[89],"overhead":[90],"or":[91],"between":[93],"responsible":[96],"consecutive":[99],"tokens.":[100],"The":[101],"task":[102,133,148,161],"scheduling":[103,134,149],"algorithm":[104,142,150,200],"crucial":[106],"minimize":[113],"TPOT":[114,205,217],"maximize":[116],"resource":[118],"utilization,":[119],"particularly":[120],"when":[121],"constrained":[125],"by":[126],"computational":[127],"capacity.":[128],"This":[129],"paper":[130],"introduces":[131],"two":[132],"algorithms,":[135,193],"improved":[137],"greedy":[138,176,196],"heuristic":[139,177,197],"shortest":[140,198],"path":[141,199],"(IGHSPA)":[143],"dynamic":[146,179],"programming-based":[147],"(DPTSA),":[151],"serving":[155],"achieve":[157],"these":[158],"objectives.":[159],"Each":[160],"involves":[162],"assigning":[163],"layer":[165],"resource,":[169],"which":[170],"IGHSPA":[171],"DPTSA":[173,215],"accomplish":[174],"using":[175],"programming.":[180],"Both":[181],"algorithms":[182],"extensively":[184],"simulated":[185],"compared":[187,230],"with":[188],"one":[189],"namely":[194],"(GHSPA),":[201],"terms":[203],"execution":[207],"(ET).":[209],"Our":[210],"simulation":[211],"results":[212],"demonstrate":[213],"improves":[216],"up":[218,225],"47.50%":[220],"35.50%":[222],"ET":[224],"99.95%":[227],"35.00%,":[229],"GHSPA":[232],"IGHSPA.":[234]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-02-19T00:00:00"}