{"id":"https://openalex.org/W4409282855","doi":"https://doi.org/10.1145/3676536.3676695","title":"ProPD: Dynamic Token Tree Pruning and Generation for LLM Parallel Decoding","display_name":"ProPD: Dynamic Token Tree Pruning and Generation for LLM Parallel Decoding","publication_year":2024,"publication_date":"2024-10-27","ids":{"openalex":"https://openalex.org/W4409282855","doi":"https://doi.org/10.1145/3676536.3676695"},"language":"en","primary_location":{"id":"doi:10.1145/3676536.3676695","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3676536.3676695","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3676536.3676695","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 43rd IEEE/ACM International Conference on Computer-Aided Design","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3676536.3676695","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081222727","display_name":"Shuzhang Zhong","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shuzhang Zhong","raw_affiliation_strings":["Institute for Artificial Intelligence, Peking University, Beijing, China","School of Integrated Circuit, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute for Artificial Intelligence, Peking University, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I20231570"]},{"raw_affiliation_string":"School of Integrated Circuit, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114950458","display_name":"Zebin Yang","orcid":"https://orcid.org/0009-0007-0672-6389"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zebin Yang","raw_affiliation_strings":["Institute for Artificial Intelligence, Peking University, Bejing, China","School of Integrated Circuit, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute for Artificial Intelligence, Peking University, Bejing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I20231570"]},{"raw_affiliation_string":"School of Integrated Circuit, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048414655","display_name":"Ruihao Gong","orcid":"https://orcid.org/0000-0002-6024-7086"},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruihao Gong","raw_affiliation_strings":["Sensetime Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Sensetime Research, Beijing, China","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002760019","display_name":"Runsheng Wang","orcid":"https://orcid.org/0000-0002-7514-0767"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4210165198","display_name":"Beijing Advanced Sciences and Innovation Center","ror":"https://ror.org/05qm21180","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165198"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Runsheng Wang","raw_affiliation_strings":["Beijing Advanced Innovation Center for Integrated Circuits, Beijing, China","Institute of Electronic Design Automation, Peking University, Wuxi, China","School of Integrated Circuit, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Advanced Innovation Center for Integrated Circuits, Beijing, China","institution_ids":["https://openalex.org/I4210165198"]},{"raw_affiliation_string":"Institute of Electronic Design Automation, Peking University, Wuxi, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"School of Integrated Circuit, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062886480","display_name":"Ru Huang","orcid":"https://orcid.org/0000-0002-8146-4821"},"institutions":[{"id":"https://openalex.org/I4210165198","display_name":"Beijing Advanced Sciences and Innovation Center","ror":"https://ror.org/05qm21180","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165198"]},{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ru Huang","raw_affiliation_strings":["Beijing Advanced Innovation Center for Integrated Circuits, Beijing, China","Institute of Electronic Design Automation, Peking University, Wxi, China","School of Integrated Circuit, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Advanced Innovation Center for Integrated Circuits, Beijing, China","institution_ids":["https://openalex.org/I4210165198"]},{"raw_affiliation_string":"Institute of Electronic Design Automation, Peking University, Wxi, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"School of Integrated Circuit, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100457502","display_name":"Meng Li","orcid":"https://orcid.org/0000-0002-7212-2264"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4210165198","display_name":"Beijing Advanced Sciences and Innovation Center","ror":"https://ror.org/05qm21180","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165198"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Li","raw_affiliation_strings":["Beijing Advanced Innovation Center for Integrated Circuits, Beijing, China","Institute for Artificial Intelligence, Peking University, Beijing, China","School of Integrated Circuit, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Advanced Innovation Center for Integrated Circuits, Beijing, China","institution_ids":["https://openalex.org/I4210165198"]},{"raw_affiliation_string":"Institute for Artificial Intelligence, Peking University, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I20231570"]},{"raw_affiliation_string":"School of Integrated Circuit, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5081222727"],"corresponding_institution_ids":["https://openalex.org/I20231570","https://openalex.org/I4210100255"],"apc_list":null,"apc_paid":null,"fwci":0.7314,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.7600629,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9965999722480774,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9965999722480774,"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/T13999","display_name":"Digital Rights Management and Security","score":0.9835000038146973,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9692999720573425,"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/security-token","display_name":"Security token","score":0.8374227285385132},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.790376603603363},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7245831489562988},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.6996647715568542},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.6048774123191833},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3624822497367859},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.20843341946601868},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.19028696417808533},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15426012873649597},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.04742234945297241}],"concepts":[{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.8374227285385132},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.790376603603363},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7245831489562988},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.6996647715568542},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.6048774123191833},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3624822497367859},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.20843341946601868},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.19028696417808533},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15426012873649597},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.04742234945297241},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3676536.3676695","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3676536.3676695","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3676536.3676695","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 43rd IEEE/ACM International Conference on Computer-Aided Design","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3676536.3676695","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3676536.3676695","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3676536.3676695","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 43rd IEEE/ACM International Conference on Computer-Aided Design","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4409282855.pdf","grobid_xml":"https://content.openalex.org/works/W4409282855.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W4294833327"],"related_works":["https://openalex.org/W4388335561","https://openalex.org/W2970530566","https://openalex.org/W4288261899","https://openalex.org/W4307309205","https://openalex.org/W2967478618","https://openalex.org/W4385009901","https://openalex.org/W4385572700","https://openalex.org/W4389471172","https://openalex.org/W4285312748","https://openalex.org/W3203767529"],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,13,27,132],"generative":[3],"large":[4,70],"language":[5,15],"models":[6],"(LLMs)":[7],"have":[8],"significantly":[9],"boosted":[10],"the":[11,24,124,129,136],"performance":[12],"natural":[14],"processing":[16],"tasks.":[17],"However,":[18],"their":[19],"efficiency":[20,138],"is":[21],"constrained":[22],"by":[23,169],"inherent":[25],"limitations":[26],"autoregressive":[28],"token":[29,35,60,91,107,118],"generation.":[30,95],"While":[31],"parallel":[32,85],"decoding":[33,45,86,167],"with":[34,52,69],"tree":[36,71,92,119],"verification,":[37],"e.g.,":[38],"Medusa,":[39],"has":[40],"been":[41],"proposed":[42],"to":[43,57,103,109,122],"improve":[44,110],"parallelism":[46,127],"and":[47,63,73,94,126,134,145,158,161],"efficiency,":[48],"it":[49,114],"often":[50],"struggles":[51],"maintaining":[53],"contextual":[54],"relationships":[55],"due":[56],"its":[58],"independent":[59],"prediction":[61],"approach":[62],"incurs":[64],"significant":[65],"verification":[66,111,130],"overhead,":[67],"especially":[68],"sizes":[72,160],"batch":[74,141,159],"processing.":[75],"In":[76],"this":[77],"paper,":[78],"we":[79],"propose":[80],"ProPD,":[81],"an":[82,98],"efficient":[83],"LLM":[84],"framework":[87],"based":[88],"on":[89],"dynamic":[90,117],"pruning":[93,101],"ProPD":[96,150,163],"features":[97],"advanced":[99],"early":[100],"mechanism":[102],"efficiently":[104],"eliminate":[105],"unpromising":[106],"sequences":[108],"efficiency.":[112],"Additionally,":[113],"introduces":[115],"a":[116,152],"generation":[120],"algorithm":[121],"balance":[123],"computation":[125],"of":[128,155],"phase":[131],"real-time":[133],"maximize":[135],"overall":[137],"across":[139,151],"different":[140],"sizes,":[142],"sequence":[143],"lengths,":[144],"tasks,":[146],"etc.":[147],"We":[148],"verify":[149],"diverse":[153],"set":[154],"datasets,":[156],"LLMs,":[157],"demonstrate":[162],"consistently":[164],"outperforms":[165],"existing":[166],"algorithms":[168],"1.1--3.2":[170],"\u00d7.":[171]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}