{"id":"https://openalex.org/W4413311652","doi":"https://doi.org/10.1145/3748355.3748372","title":"eInfer: Unlocking Fine-Grained Tracing for Distributed LLM Inference with eBPF","display_name":"eInfer: Unlocking Fine-Grained Tracing for Distributed LLM Inference with eBPF","publication_year":2025,"publication_date":"2025-08-19","ids":{"openalex":"https://openalex.org/W4413311652","doi":"https://doi.org/10.1145/3748355.3748372"},"language":"en","primary_location":{"id":"doi:10.1145/3748355.3748372","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3748355.3748372","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd Workshop on eBPF and Kernel Extensions","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":null,"display_name":"Kexin Chu","orcid":"https://orcid.org/0009-0000-0303-6699"},"institutions":[{"id":"https://openalex.org/I140172145","display_name":"University of Connecticut","ror":"https://ror.org/02der9h97","country_code":"US","type":"education","lineage":["https://openalex.org/I140172145"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kexin Chu","raw_affiliation_strings":["University of Connecticut, Storrs, CT, USA"],"raw_orcid":"https://orcid.org/0009-0000-0303-6699","affiliations":[{"raw_affiliation_string":"University of Connecticut, Storrs, CT, USA","institution_ids":["https://openalex.org/I140172145"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004251735","display_name":"Jianchang Su","orcid":"https://orcid.org/0000-0002-4089-8316"},"institutions":[{"id":"https://openalex.org/I140172145","display_name":"University of Connecticut","ror":"https://ror.org/02der9h97","country_code":"US","type":"education","lineage":["https://openalex.org/I140172145"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jianchang Su","raw_affiliation_strings":["University of Connecticut, Storrs, CT, USA"],"raw_orcid":"https://orcid.org/0000-0002-4089-8316","affiliations":[{"raw_affiliation_string":"University of Connecticut, Storrs, CT, USA","institution_ids":["https://openalex.org/I140172145"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035079429","display_name":"Yifan Zhang","orcid":"https://orcid.org/0009-0005-6403-2161"},"institutions":[{"id":"https://openalex.org/I140172145","display_name":"University of Connecticut","ror":"https://ror.org/02der9h97","country_code":"US","type":"education","lineage":["https://openalex.org/I140172145"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yifan Zhang","raw_affiliation_strings":["University of Connecticut, Storrs, CT, USA"],"raw_orcid":"https://orcid.org/0009-0005-6403-2161","affiliations":[{"raw_affiliation_string":"University of Connecticut, Storrs, CT, USA","institution_ids":["https://openalex.org/I140172145"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019750903","display_name":"Chenxingyu Zhao","orcid":"https://orcid.org/0000-0001-8528-1689"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chenxingyu Zhao","raw_affiliation_strings":["University of Washington, Seattle, WA, USA"],"raw_orcid":"https://orcid.org/0000-0001-8528-1689","affiliations":[{"raw_affiliation_string":"University of Washington, Seattle, WA, USA","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103214236","display_name":"Yiwei Yang","orcid":"https://orcid.org/0000-0001-8011-5868"},"institutions":[{"id":"https://openalex.org/I185103710","display_name":"University of California, Santa Cruz","ror":"https://ror.org/03s65by71","country_code":"US","type":"education","lineage":["https://openalex.org/I185103710"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yiwei Yang","raw_affiliation_strings":["UC Santa Cruz, Santa Cruz, CA, USA"],"raw_orcid":"https://orcid.org/0000-0001-8011-5868","affiliations":[{"raw_affiliation_string":"UC Santa Cruz, Santa Cruz, CA, USA","institution_ids":["https://openalex.org/I185103710"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110949983","display_name":"Yusheng Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I185103710","display_name":"University of California, Santa Cruz","ror":"https://ror.org/03s65by71","country_code":"US","type":"education","lineage":["https://openalex.org/I185103710"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yusheng Zheng","raw_affiliation_strings":["UC Santa Cruz, Santa Cruz, CA, USA"],"raw_orcid":"https://orcid.org/0009-0004-3193-4356","affiliations":[{"raw_affiliation_string":"UC Santa Cruz, Santa Cruz, CA, USA","institution_ids":["https://openalex.org/I185103710"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052342255","display_name":"Shengkai Lin","orcid":"https://orcid.org/0009-0003-2615-0525"},"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":"Shengkai Lin","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0003-2615-0525","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075325244","display_name":"Shizhen Zhao","orcid":"https://orcid.org/0000-0001-8395-5109"},"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":"Shizhen Zhao","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-8395-5109","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100577526","display_name":"Wei Zhang","orcid":"https://orcid.org/0009-0004-9512-4192"},"institutions":[{"id":"https://openalex.org/I140172145","display_name":"University of Connecticut","ror":"https://ror.org/02der9h97","country_code":"US","type":"education","lineage":["https://openalex.org/I140172145"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Zhang","raw_affiliation_strings":["University of Connecticut, Storrs, CT, USA"],"raw_orcid":"https://orcid.org/0009-0004-9512-4192","affiliations":[{"raw_affiliation_string":"University of Connecticut, Storrs, CT, USA","institution_ids":["https://openalex.org/I140172145"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"76","last_page":"83"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10927","display_name":"Access Control and Trust","score":0.9836999773979187,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10927","display_name":"Access Control and Trust","score":0.9836999773979187,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12326","display_name":"Network Packet Processing and Optimization","score":0.9699000120162964,"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"}},{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9592999815940857,"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/computer-science","display_name":"Computer science","score":0.7309109568595886},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6496070623397827},{"id":"https://openalex.org/keywords/tracing","display_name":"Tracing","score":0.6164745688438416},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.18128514289855957},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1670462191104889}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7309109568595886},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6496070623397827},{"id":"https://openalex.org/C138673069","wikidata":"https://www.wikidata.org/wiki/Q322229","display_name":"Tracing","level":2,"score":0.6164745688438416},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.18128514289855957},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1670462191104889}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3748355.3748372","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3748355.3748372","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd Workshop on eBPF and Kernel Extensions","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5099999904632568,"id":"https://metadata.un.org/sdg/2","display_name":"Zero hunger"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W95608104","https://openalex.org/W3129485837","https://openalex.org/W3197979949","https://openalex.org/W4286308005","https://openalex.org/W4381744943","https://openalex.org/W4381744979","https://openalex.org/W4384345619","https://openalex.org/W4386378095","https://openalex.org/W4388661866","https://openalex.org/W4393147278","https://openalex.org/W4405756183","https://openalex.org/W4405845970","https://openalex.org/W4408869788","https://openalex.org/W4408894415","https://openalex.org/W4409248734","https://openalex.org/W4409474901","https://openalex.org/W4409714186","https://openalex.org/W4411337585"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2888673113","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2056065966","https://openalex.org/W2376932109"],"abstract_inverted_index":{"Modern":[0],"large":[1],"language":[2],"model":[3],"(LLM)":[4],"inference":[5,63],"workloads":[6],"run":[7],"on":[8,103],"complex,":[9],"heterogeneous":[10],"distributed":[11,61],"systems":[12],"spanning":[13],"CPUs,":[14,74],"GPUs,":[15],"multi-GPU":[16],"setups,":[17],"and":[18,77,100],"network":[19],"interconnects.":[20],"Existing":[21],"profiling":[22,90],"tools":[23],"either":[24],"incur":[25],"prohibitive":[26],"overhead,":[27],"provide":[28],"limited":[29],"visibility,":[30],"or":[31],"suffer":[32],"from":[33],"vendor":[34],"lock-in,":[35],"making":[36],"real-time,":[37],"fine-grained":[38],"performance":[39,59,135],"analysis":[40],"impractical":[41],"in":[42,115,136],"production":[43,137],"environments.":[44,138],"We":[45],"present":[46],"eInfer,":[47],"the":[48,85,94],"first":[49],"eBPF-based":[50],"system":[51],"enabling":[52,128],"transparent,":[53],"low-overhead":[54,126],"end-to-end":[55],"tracing":[56,109],"of":[57,87,96],"per-request":[58],"across":[60,73],"LLM":[62,133],"pipelines":[64],"without":[65],"requiring":[66],"application":[67],"modifications.":[68],"eInfer":[69,123],"uniquely":[70],"correlates":[71],"events":[72],"accelerators,":[75,104],"processes,":[76],"nodes,":[78],"delivering":[79],"unified,":[80],"vendor-agnostic":[81],"observability":[82],"that":[83,111,122],"approaches":[84],"accuracy":[86],"specialized":[88],"GPU":[89],"tools.":[91],"To":[92],"address":[93],"challenges":[95],"scalability":[97],"dynamic":[98],"workloads,":[99],"instrumentation":[101],"gaps":[102],"we":[105],"design":[106],"a":[107],"runtime-adaptive":[108],"mechanism":[110],"maintains":[112],"comprehensive":[113],"visibility":[114],"real":[116],"time.":[117],"Our":[118],"initial":[119],"evaluation":[120],"demonstrates":[121],"delivers":[124],"precise,":[125],"profiling,":[127],"critical":[129],"insights":[130],"to":[131],"optimize":[132],"serving":[134]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}