{"id":"https://openalex.org/W4407953495","doi":"https://doi.org/10.1145/3706628.3708863","title":"FMC-LLM: Enabling FPGAs for Efficient Batched Decoding of 70B+ LLMs with a Memory-Centric Streaming Architecture","display_name":"FMC-LLM: Enabling FPGAs for Efficient Batched Decoding of 70B+ LLMs with a Memory-Centric Streaming Architecture","publication_year":2025,"publication_date":"2025-02-26","ids":{"openalex":"https://openalex.org/W4407953495","doi":"https://doi.org/10.1145/3706628.3708863"},"language":"en","primary_location":{"id":"doi:10.1145/3706628.3708863","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3706628.3708863","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3706628.3708863","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 ACM/SIGDA International Symposium on Field Programmable Gate Arrays","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/10.1145/3706628.3708863","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074195618","display_name":"Wenheng Ma","orcid":"https://orcid.org/0000-0003-2349-7286"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wenheng Ma","raw_affiliation_strings":["Tsinghua University, Beijing, China and Infinigence-AI, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2349-7286","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China and Infinigence-AI, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020244808","display_name":"Xinhao Yang","orcid":"https://orcid.org/0009-0001-9739-2930"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinhao Yang","raw_affiliation_strings":["Tsinghua University, Beijing, China and Infinigence-AI, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-9739-2930","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China and Infinigence-AI, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026831784","display_name":"Shulin Zeng","orcid":"https://orcid.org/0000-0002-1030-3748"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shulin Zeng","raw_affiliation_strings":["Tsinghua University, Beijing, China and Infinigence-AI, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1030-3748","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China and Infinigence-AI, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083660349","display_name":"Tengxuan Liu","orcid":"https://orcid.org/0009-0007-8943-1577"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tengxuan Liu","raw_affiliation_strings":["Tsinghua University, Beijing, China and Infinigence-AI, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-8943-1577","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China and Infinigence-AI, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079946965","display_name":"Libo Shen","orcid":"https://orcid.org/0009-0000-1717-2093"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Libo Shen","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0009-0000-1717-2093","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023007010","display_name":"Hongyi Wang","orcid":"https://orcid.org/0009-0008-7095-7963"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongyi Wang","raw_affiliation_strings":["Tsinghua University, Beijing, China and Infinigence-AI, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-7095-7963","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China and Infinigence-AI, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005872704","display_name":"Shiyao Li","orcid":"https://orcid.org/0009-0007-4755-6881"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiyao Li","raw_affiliation_strings":["Tsinghua University, Beijing, China and Infinigence-AI, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-4755-6881","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China and Infinigence-AI, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jiewen Wang","orcid":"https://orcid.org/0009-0001-9611-4277"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiewen Wang","raw_affiliation_strings":["Infinigence-AI, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-9611-4277","affiliations":[{"raw_affiliation_string":"Infinigence-AI, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yuhan Zhang","orcid":"https://orcid.org/0009-0002-6146-2826"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuhan Zhang","raw_affiliation_strings":["Infinigence-AI, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-6146-2826","affiliations":[{"raw_affiliation_string":"Infinigence-AI, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hao Guo","orcid":"https://orcid.org/0009-0004-3143-1740"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao Guo","raw_affiliation_strings":["Infinigence-AI, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-3143-1740","affiliations":[{"raw_affiliation_string":"Infinigence-AI, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053894346","display_name":"Jintao Li","orcid":"https://orcid.org/0009-0006-8903-8276"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jintao Li","raw_affiliation_strings":["Infinigence-AI, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-8903-8276","affiliations":[{"raw_affiliation_string":"Infinigence-AI, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ziming Zhang","orcid":"https://orcid.org/0009-0004-8567-2849"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziming Zhang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-8567-2849","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103138440","display_name":"Zhenhua Zhu","orcid":"https://orcid.org/0009-0007-9259-7180"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenhua Zhu","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-9259-7180","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086217226","display_name":"Xuefei Ning","orcid":"https://orcid.org/0000-0003-2209-8312"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuefei Ning","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2209-8312","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062800747","display_name":"Tsung-Yi Ho","orcid":"https://orcid.org/0000-0001-7348-5625"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Tsung-Yi Ho","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0001-7348-5625","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015946486","display_name":"Guohao Dai","orcid":"https://orcid.org/0000-0003-0849-3252"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guohao Dai","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China and Infinigence-AI, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-0849-3252","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China and Infinigence-AI, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100445061","display_name":"Yu Wang","orcid":"https://orcid.org/0000-0001-6108-5157"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Wang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6108-5157","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":17,"corresponding_author_ids":["https://openalex.org/A5074195618"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":4.3465,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.93248551,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"55","last_page":"55"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9975000023841858,"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"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9975000023841858,"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"}},{"id":"https://openalex.org/T12029","display_name":"DNA and Biological Computing","score":0.991599977016449,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9832000136375427,"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/decoding-methods","display_name":"Decoding methods","score":0.7496129274368286},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6609009504318237},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.6304887533187866},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5664019584655762},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.42697107791900635},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.4125269055366516},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.32352161407470703},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.16686025261878967}],"concepts":[{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.7496129274368286},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6609009504318237},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.6304887533187866},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5664019584655762},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.42697107791900635},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.4125269055366516},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.32352161407470703},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.16686025261878967},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3706628.3708863","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3706628.3708863","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3706628.3708863","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 ACM/SIGDA International Symposium on Field Programmable Gate Arrays","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3706628.3708863","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3706628.3708863","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3706628.3708863","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 ACM/SIGDA International Symposium on Field Programmable Gate Arrays","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.5699999928474426}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4407953495.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2111241003","https://openalex.org/W2355315220","https://openalex.org/W2096844293","https://openalex.org/W2363944576","https://openalex.org/W2351041855","https://openalex.org/W2570254841","https://openalex.org/W1967938402","https://openalex.org/W2386041993","https://openalex.org/W1608572506","https://openalex.org/W2038503502"],"abstract_inverted_index":{"For":[0],"large":[1],"language":[2],"model":[3,19],"(LLM)":[4],"acceleration,":[5],"FPGAs":[6,27],"face":[7],"two":[8],"challenges:":[9],"insufficient":[10],"peak":[11],"computing":[12],"performance":[13],"and":[14],"unacceptable":[15],"accuracy":[16],"loss":[17],"of":[18,32],"compression.":[20],"This":[21],"paper":[22],"proposes":[23],"FMC-LLM":[24],"to":[25],"enable":[26],"for":[28],"efficient":[29],"batched":[30],"decoding":[31],"70B+":[33],"LLMs.":[34]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}
