{"id":"https://openalex.org/W4411486323","doi":"https://doi.org/10.1145/3695053.3731024","title":"Ecco: Improving Memory Bandwidth and Capacity for LLMs via Entropy-Aware Cache Compression","display_name":"Ecco: Improving Memory Bandwidth and Capacity for LLMs via Entropy-Aware Cache Compression","publication_year":2025,"publication_date":"2025-06-20","ids":{"openalex":"https://openalex.org/W4411486323","doi":"https://doi.org/10.1145/3695053.3731024"},"language":"en","primary_location":{"id":"doi:10.1145/3695053.3731024","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3695053.3731024","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3695053.3731024","source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 52nd Annual International Symposium on Computer Architecture","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/10.1145/3695053.3731024","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000945196","display_name":"Feng Cheng","orcid":"https://orcid.org/0000-0002-5936-0030"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Feng Cheng","raw_affiliation_strings":["Duke University, Durham, USA"],"raw_orcid":"https://orcid.org/0000-0002-5936-0030","affiliations":[{"raw_affiliation_string":"Duke University, Durham, USA","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101706991","display_name":"Cong Guo","orcid":"https://orcid.org/0000-0002-4479-5525"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cong Guo","raw_affiliation_strings":["Duke University, Durham, USA"],"raw_orcid":"https://orcid.org/0000-0002-4479-5525","affiliations":[{"raw_affiliation_string":"Duke University, Durham, USA","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060545776","display_name":"Chiyue Wei","orcid":"https://orcid.org/0009-0008-8815-7948"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chiyue Wei","raw_affiliation_strings":["Duke University, Durham, USA"],"raw_orcid":"https://orcid.org/0009-0008-8815-7948","affiliations":[{"raw_affiliation_string":"Duke University, Durham, USA","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100749754","display_name":"Junyao Zhang","orcid":"https://orcid.org/0009-0008-3913-7879"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]},{"id":"https://openalex.org/I4210137977","display_name":"Advanced Micro Devices (United States)","ror":"https://ror.org/04kd6c783","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137977"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Junyao Zhang","raw_affiliation_strings":["Advanced Micro Devices, Inc., Santa Clara, USA","Duke University, Durham, USA"],"raw_orcid":"https://orcid.org/0009-0008-3913-7879","affiliations":[{"raw_affiliation_string":"Advanced Micro Devices, Inc., Santa Clara, USA","institution_ids":["https://openalex.org/I4210137977"]},{"raw_affiliation_string":"Duke University, Durham, USA","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088778898","display_name":"Changchun Zhou","orcid":"https://orcid.org/0009-0005-3968-5048"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Changchun Zhou","raw_affiliation_strings":["Duke University, Durham, USA"],"raw_orcid":"https://orcid.org/0009-0005-3968-5048","affiliations":[{"raw_affiliation_string":"Duke University, Durham, USA","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074284629","display_name":"Edward Hanson","orcid":"https://orcid.org/0000-0001-5179-8401"},"institutions":[{"id":"https://openalex.org/I4210137977","display_name":"Advanced Micro Devices (United States)","ror":"https://ror.org/04kd6c783","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137977"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Edward Hanson","raw_affiliation_strings":["Advanced Micro Devices, Inc., Santa Clara, USA"],"raw_orcid":"https://orcid.org/0000-0001-5179-8401","affiliations":[{"raw_affiliation_string":"Advanced Micro Devices, Inc., Santa Clara, USA","institution_ids":["https://openalex.org/I4210137977"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100349804","display_name":"Jiaqi Zhang","orcid":"https://orcid.org/0000-0002-3714-3414"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]},{"id":"https://openalex.org/I4210137977","display_name":"Advanced Micro Devices (United States)","ror":"https://ror.org/04kd6c783","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137977"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiaqi Zhang","raw_affiliation_strings":["Advanced Micro Devices, Inc., Santa Clara, USA","Duke University, Durham, USA"],"raw_orcid":"https://orcid.org/0000-0002-3714-3414","affiliations":[{"raw_affiliation_string":"Advanced Micro Devices, Inc., Santa Clara, USA","institution_ids":["https://openalex.org/I4210137977"]},{"raw_affiliation_string":"Duke University, Durham, USA","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100338879","display_name":"Xiaoxiao Liu","orcid":"https://orcid.org/0000-0001-6325-1796"},"institutions":[{"id":"https://openalex.org/I4210137977","display_name":"Advanced Micro Devices (United States)","ror":"https://ror.org/04kd6c783","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137977"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaoxiao Liu","raw_affiliation_strings":["Advanced Micro Devices, Inc., Santa Clara, USA"],"raw_orcid":"https://orcid.org/0000-0001-6325-1796","affiliations":[{"raw_affiliation_string":"Advanced Micro Devices, Inc., Santa Clara, USA","institution_ids":["https://openalex.org/I4210137977"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100429403","display_name":"Hai Li","orcid":"https://orcid.org/0000-0003-3228-6544"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hai Li","raw_affiliation_strings":["Duke University, Durham, USA"],"raw_orcid":"https://orcid.org/0000-0003-3228-6544","affiliations":[{"raw_affiliation_string":"Duke University, Durham, USA","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058073627","display_name":"Yiran Chen","orcid":"https://orcid.org/0000-0002-1486-8412"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yiran Chen","raw_affiliation_strings":["Duke University, Durham, USA"],"raw_orcid":"https://orcid.org/0000-0002-1486-8412","affiliations":[{"raw_affiliation_string":"Duke University, Durham, USA","institution_ids":["https://openalex.org/I170897317"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":11.8343,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.98789004,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"793","last_page":"807"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9991999864578247,"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":0.9991999864578247,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9980999827384949,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9901999831199646,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/computer-science","display_name":"Computer science","score":0.6263754963874817},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.49641114473342896},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.4130851924419403},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.2897440791130066},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.182728111743927}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6263754963874817},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.49641114473342896},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.4130851924419403},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.2897440791130066},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.182728111743927}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3695053.3731024","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3695053.3731024","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3695053.3731024","source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 52nd Annual International Symposium on Computer Architecture","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3695053.3731024","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3695053.3731024","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3695053.3731024","source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 52nd Annual International Symposium on Computer Architecture","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.8100000023841858}],"awards":[{"id":"https://openalex.org/G6624552157","display_name":null,"funder_award_id":"W911NF-23-2-0224","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G7452299184","display_name":null,"funder_award_id":"W911NF","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G7685286239","display_name":null,"funder_award_id":"ARO W911NF-23-2-0224","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G8377316191","display_name":"AI Institute for Edge Computing Leveraging Next Generation Networks (Athena)","funder_award_id":"2112562","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320307757","display_name":"Advanced Micro Devices","ror":"https://ror.org/04kd6c783"},{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411486323.pdf","grobid_xml":"https://content.openalex.org/works/W4411486323.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W1976494130","https://openalex.org/W2060108852","https://openalex.org/W2140196014","https://openalex.org/W2162752393","https://openalex.org/W2285660444","https://openalex.org/W2883283076","https://openalex.org/W2897962465","https://openalex.org/W2946609015","https://openalex.org/W2979340153","https://openalex.org/W3043802286","https://openalex.org/W3102510044","https://openalex.org/W3130554079","https://openalex.org/W3194676777","https://openalex.org/W4225000412","https://openalex.org/W4308083739","https://openalex.org/W4308083831","https://openalex.org/W4366341968","https://openalex.org/W4382246105","https://openalex.org/W4387321091","https://openalex.org/W4389476167","https://openalex.org/W4391827186","https://openalex.org/W4403211793","https://openalex.org/W4407212618","https://openalex.org/W4409248468","https://openalex.org/W4409248600","https://openalex.org/W6893007900"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"(LLMs)":[3],"have":[4,29],"demonstrated":[5],"transformative":[6],"capabilities":[7],"across":[8],"diverse":[9],"artificial":[10],"intelligence":[11],"applications,":[12],"yet":[13],"their":[14],"deployment":[15],"is":[16],"hindered":[17],"by":[18,120,162],"substantial":[19],"memory":[20,40,160],"and":[21,41,52,72,80,103,125,142,149,165],"computational":[22,42],"demands,":[23],"especially":[24],"in":[25,99],"resource-constrained":[26],"environments.Quantization":[27],"techniques":[28],"emerged":[30],"as":[31],"a":[32,107,114],"critical":[33],"solution,":[34],"reducing":[35,118],"data":[36],"precision":[37],"to":[38,83,129,140],"enhance":[39],"efficiency.However,":[43],"existing":[44],"methods":[45],"often":[46],"suffer":[47],"from":[48],"high":[49],"runtime":[50],"overheads":[51],"potential":[53],"accuracy":[54],"degradation.To":[55],"address":[56],"these":[57],"challenges,":[58],"we":[59,105],"propose":[60],"Ecco,":[61],"an":[62,138],"entropy-based":[63],"cache":[64,91],"compression":[65],"technique":[66],"tailored":[67],"for":[68],"LLMs.Ecco":[69],"combines":[70],"group-wise":[71],"nonuniform":[73],"quantization":[74],"with":[75,113],"pre-defined":[76],"shared":[77],"k-means":[78],"patterns":[79],"Huffman":[81,97],"coding":[82,98],"exploit":[84],"the":[85,93,146,154,172],"inherent":[86],"entropy":[87],"characteristics":[88],"of":[89,95,101,123,174],"LLM":[90,168],"data.Recognizing":[92],"inefficiencies":[94],"traditional":[96],"terms":[100],"parallelism":[102],"latency,":[104],"introduce":[106],"novel":[108],"parallel":[109],"Huffman-based":[110],"decoding":[111],"process":[112],"multi-stage":[115],"pipeline":[116],"design,":[117],"latency":[119],"two":[121],"orders":[122],"magnitude":[124],"achieving":[126],"throughput":[127],"comparable":[128],"GPU":[130],"L2":[131],"caches.Comprehensive":[132],"evaluations":[133],"demonstrate":[134],"that":[135],"Ecco":[136],"achieves":[137],"up":[139],"2.9\u00d7":[141],"1.9\u00d7":[143],"speedup":[144],"over":[145,153],"state-of-the-art":[147,167],"AWQ":[148],"SmoothQuant":[150],"framework,":[151],"2.4\u00d7":[152],"Olive":[155],"accelerator,":[156],"all":[157],"while":[158],"increasing":[159],"capacity":[161],"nearly":[163],"4\u00d7":[164],"maintaining":[166],"accuracy.These":[169],"results":[170],"underscore":[171],"effectiveness":[173],"our":[175]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-31T08:31:51.225901","created_date":"2025-10-10T00:00:00"}
