{"id":"https://openalex.org/W7172379742","doi":"https://doi.org/10.1109/isca66397.2026.00054","title":"HybridSpec: Exploiting Hybrid-Bonding Memory to Accelerate LLM Serving Through Heterogeneous Architecture and Speculative Decoding","display_name":"HybridSpec: Exploiting Hybrid-Bonding Memory to Accelerate LLM Serving Through Heterogeneous Architecture and Speculative Decoding","publication_year":2026,"publication_date":"2026-06-01","ids":{"openalex":"https://openalex.org/W7172379742","doi":"https://doi.org/10.1109/isca66397.2026.00054"},"language":null,"primary_location":{"id":"doi:10.1109/isca66397.2026.00054","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isca66397.2026.00054","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 ACM/IEEE 53rd Annual International Symposium on Computer Architecture (ISCA)","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/A5114189100","display_name":"Zongle Huang","orcid":"https://orcid.org/0009-0002-4557-3163"},"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":"Zongle Huang","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042337656","display_name":"Wenbin Jia","orcid":null},"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":"Wenbin Jia","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046057730","display_name":"Yaolei Li","orcid":"https://orcid.org/0000-0002-6640-1275"},"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":"Yaolei Li","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039208284","display_name":"Xinyuan Lin","orcid":"https://orcid.org/0009-0002-6881-5348"},"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":"Xinyuan Lin","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027809257","display_name":"Shupei Fan","orcid":"https://orcid.org/0009-0004-5314-3002"},"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":"Shupei Fan","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5144382425","display_name":"Chen Tang","orcid":null},"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":"Chen Tang","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5144319701","display_name":"Shuwen Deng","orcid":null},"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":"Shuwen Deng","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5144343328","display_name":"Yongpan Liu","orcid":null},"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":"Yongpan Liu","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"588","last_page":"603"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5022000074386597},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.42149999737739563},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.3628999888896942},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.34700000286102295},{"id":"https://openalex.org/keywords/random-access-memory","display_name":"Random access memory","score":0.30970001220703125},{"id":"https://openalex.org/keywords/memory-management","display_name":"Memory management","score":0.3093000054359436}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7429999709129333},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5022000074386597},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.42149999737739563},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.36739999055862427},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3628999888896942},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3513000011444092},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.34700000286102295},{"id":"https://openalex.org/C2994168587","wikidata":"https://www.wikidata.org/wiki/Q5295","display_name":"Random access memory","level":2,"score":0.30970001220703125},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.3093000054359436},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.2957000136375427},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2874000072479248},{"id":"https://openalex.org/C98025372","wikidata":"https://www.wikidata.org/wiki/Q477538","display_name":"Systems architecture","level":3,"score":0.2712000012397766},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.26420000195503235},{"id":"https://openalex.org/C2779602883","wikidata":"https://www.wikidata.org/wiki/Q15544750","display_name":"Memory architecture","level":2,"score":0.26030001044273376},{"id":"https://openalex.org/C20136886","wikidata":"https://www.wikidata.org/wiki/Q749647","display_name":"Interoperability","level":2,"score":0.25619998574256897}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/isca66397.2026.00054","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isca66397.2026.00054","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 ACM/IEEE 53rd Annual International Symposium on Computer Architecture (ISCA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W2048266589","https://openalex.org/W2113320347","https://openalex.org/W2118950608","https://openalex.org/W2173259163","https://openalex.org/W2291863645","https://openalex.org/W2518432791","https://openalex.org/W2593197747","https://openalex.org/W2787701666","https://openalex.org/W2926767350","https://openalex.org/W2940862705","https://openalex.org/W2980104813","https://openalex.org/W3015587302","https://openalex.org/W3016166938","https://openalex.org/W3136346557","https://openalex.org/W4220972538","https://openalex.org/W4283076324","https://openalex.org/W4285217154","https://openalex.org/W4292261931","https://openalex.org/W4385192563","https://openalex.org/W4385245566","https://openalex.org/W4387321091","https://openalex.org/W4389518760","https://openalex.org/W4392427708","https://openalex.org/W4392746501","https://openalex.org/W4393407316","https://openalex.org/W4395034968","https://openalex.org/W4395073431","https://openalex.org/W4395106409","https://openalex.org/W4395112660","https://openalex.org/W4401211704","https://openalex.org/W4401211878","https://openalex.org/W4402670335","https://openalex.org/W4402683901","https://openalex.org/W4407218342","https://openalex.org/W4408925909","https://openalex.org/W4409248462","https://openalex.org/W4411485931","https://openalex.org/W4414197279","https://openalex.org/W4415797132","https://openalex.org/W4415798602","https://openalex.org/W4416429558"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-08-11T07:18:39.950985","created_date":"2026-08-05T00:00:00"}
