{"id":"https://openalex.org/W4412016708","doi":"https://doi.org/10.1145/3719276.3727954","title":"POSTER: V-Seek: Optimizing LLM Reasoning on A Server-Class General-Purpose RISC-V Platform","display_name":"POSTER: V-Seek: Optimizing LLM Reasoning on A Server-Class General-Purpose RISC-V Platform","publication_year":2025,"publication_date":"2025-05-28","ids":{"openalex":"https://openalex.org/W4412016708","doi":"https://doi.org/10.1145/3719276.3727954"},"language":"en","primary_location":{"id":"doi:10.1145/3719276.3727954","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3719276.3727954","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3719276.3727954","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd ACM International Conference on Computing Frontiers","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3719276.3727954","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5118815789","display_name":"Javier Jesus Poveda Rodrigo","orcid":null},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Politecnico di Torino","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Javier Jesus Poveda Rodrigo","raw_affiliation_strings":["Politecnico di Torino, Turin, Italy"],"raw_orcid":"https://orcid.org/0009-0003-3115-3464","affiliations":[{"raw_affiliation_string":"Politecnico di Torino, Turin, Italy","institution_ids":["https://openalex.org/I177477856"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032352696","display_name":"Mohamed Amine Hamdi","orcid":"https://orcid.org/0009-0006-0539-5007"},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Politecnico di Torino","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Mohamed Amine Hamdi","raw_affiliation_strings":["Politecnico di Torino, Turin, Italy"],"raw_orcid":"https://orcid.org/0009-0006-0539-5007","affiliations":[{"raw_affiliation_string":"Politecnico di Torino, Turin, Italy","institution_ids":["https://openalex.org/I177477856"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115751364","display_name":"Cyril Koenig","orcid":null},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Cyril Koenig","raw_affiliation_strings":["ETH Z\u00fcrich, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0009-0007-9771-1691","affiliations":[{"raw_affiliation_string":"ETH Z\u00fcrich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032095821","display_name":"Alessio Burrello","orcid":"https://orcid.org/0000-0002-6215-8220"},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Politecnico di Torino","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alessio Burrello","raw_affiliation_strings":["Politecnico di Torino, Turin, Italy"],"raw_orcid":"https://orcid.org/0000-0002-6215-8220","affiliations":[{"raw_affiliation_string":"Politecnico di Torino, Turin, Italy","institution_ids":["https://openalex.org/I177477856"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080843266","display_name":"Daniele Jahier Pagliari","orcid":"https://orcid.org/0000-0002-2872-7071"},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Politecnico di Torino","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Daniele Jahier Pagliari","raw_affiliation_strings":["Politecnico di Torino, Turin, Italy"],"raw_orcid":"https://orcid.org/0000-0002-2872-7071","affiliations":[{"raw_affiliation_string":"Politecnico di Torino, Turin, Italy","institution_ids":["https://openalex.org/I177477856"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043408422","display_name":"Luca Benini","orcid":"https://orcid.org/0000-0001-8068-3806"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Luca Benini","raw_affiliation_strings":["ETH Z\u00fcrich, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0001-8068-3806","affiliations":[{"raw_affiliation_string":"ETH Z\u00fcrich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5529,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.78798613,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"224","last_page":"225"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9399999976158142,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9399999976158142,"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/T10679","display_name":"Service-Oriented Architecture and Web Services","score":0.9193999767303467,"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/T11195","display_name":"Simulation Techniques and Applications","score":0.9089999794960022,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7449566721916199},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.6882030367851257},{"id":"https://openalex.org/keywords/reduced-instruction-set-computing","display_name":"Reduced instruction set computing","score":0.4821128845214844},{"id":"https://openalex.org/keywords/general-purpose","display_name":"General purpose","score":0.4157858192920685},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3794507086277008},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.364238977432251},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3274030089378357},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.2097541093826294},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1211341917514801}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7449566721916199},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.6882030367851257},{"id":"https://openalex.org/C126298526","wikidata":"https://www.wikidata.org/wiki/Q189376","display_name":"Reduced instruction set computing","level":3,"score":0.4821128845214844},{"id":"https://openalex.org/C2982832238","wikidata":"https://www.wikidata.org/wiki/Q5531640","display_name":"General purpose","level":2,"score":0.4157858192920685},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3794507086277008},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.364238977432251},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3274030089378357},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.2097541093826294},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1211341917514801}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3719276.3727954","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3719276.3727954","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3719276.3727954","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd ACM International Conference on Computing Frontiers","raw_type":"proceedings-article"},{"id":"pmh:oai:cris.unibo.it:11585/1040753","is_oa":false,"landing_page_url":"https://hdl.handle.net/11585/1040753","pdf_url":null,"source":{"id":"https://openalex.org/S4306402579","display_name":"Archivio istituzionale della ricerca (Alma Mater Studiorum Universit\u00e0 di Bologna)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210117483","host_organization_name":"Istituto di Ematologia di Bologna","host_organization_lineage":["https://openalex.org/I4210117483"],"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":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.1145/3719276.3727954","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3719276.3727954","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3719276.3727954","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd ACM International Conference on Computing Frontiers","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412016708.pdf","grobid_xml":"https://content.openalex.org/works/W4412016708.grobid-xml"},"referenced_works_count":2,"referenced_works":["https://openalex.org/W4399304422","https://openalex.org/W4405381968"],"related_works":["https://openalex.org/W2418291489","https://openalex.org/W2035206467","https://openalex.org/W2512308948","https://openalex.org/W2068921804","https://openalex.org/W2163814585","https://openalex.org/W3136156262","https://openalex.org/W7324480","https://openalex.org/W2533728829","https://openalex.org/W89880274","https://openalex.org/W2259750238"],"abstract_inverted_index":{"This":[0],"paper":[1],"addresses":[2],"the":[3,18,22,49,83],"problem":[4],"of":[5,7,25,48,57,66,74,82],"deployment":[6],"LLMs":[8,28],"on":[9,17,46],"RISC-V-based":[10],"CPU":[11],"systems":[12],"by":[13],"optimizing":[14],"LLM":[15],"inference":[16,23],"Sophon":[19],"SG2042.We":[20],"evaluate":[21],"performance":[24],"two":[26],"state-of-theart":[27],"optimised":[29],"for":[30],"reasoning:":[31],"DeepSeek":[32,38],"R1":[33,39],"Distill":[34,40],"Llama":[35],"8B":[36],"and":[37,62],"QWEN":[41],"14B.Thanks":[42],"to":[43,76,78],"our":[44],"optimizations":[45],"top":[47],"llama.cppinference":[50],"library,":[51],"we":[52],"achieve":[53],"token":[54],"generation":[55],"speeds":[56,65],"4.32/2.29":[58],"tokens":[59],"per":[60,68],"second":[61],"prompt":[63],"processing":[64],"6.54/3.68tokens":[67],"second,":[69],"with":[70],"a":[71,79],"significant":[72],"speedup":[73],"up":[75],"2.9\u00d7/3.0\u00d7compared":[77],"direct":[80],"porting":[81],"same":[84],"library.":[85]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}
