{"id":"https://openalex.org/W7134918311","doi":"https://doi.org/10.1145/3779212.3790219","title":"Shift Parallelism: Low-Latency, High-Throughput LLM Inference for Dynamic Workloads","display_name":"Shift Parallelism: Low-Latency, High-Throughput LLM Inference for Dynamic Workloads","publication_year":2026,"publication_date":"2026-03-10","ids":{"openalex":"https://openalex.org/W7134918311","doi":"https://doi.org/10.1145/3779212.3790219"},"language":null,"primary_location":{"id":"doi:10.1145/3779212.3790219","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3779212.3790219","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3779212.3790219","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024169920","display_name":"Mert Hidayeto\u011flu","orcid":"https://orcid.org/0000-0001-9276-5075"},"institutions":[{"id":"https://openalex.org/I18332796","display_name":"Snow College","ror":"https://ror.org/04azdj983","country_code":"US","type":"education","lineage":["https://openalex.org/I18332796"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mert Hidayetoglu","raw_affiliation_strings":["Snowflake, Menlo Park, USA"],"raw_orcid":"https://orcid.org/0000-0001-9276-5075","affiliations":[{"raw_affiliation_string":"Snowflake, Menlo Park, USA","institution_ids":["https://openalex.org/I18332796"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073820927","display_name":"Aurick Qiao","orcid":"https://orcid.org/0009-0004-9119-8696"},"institutions":[{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aurick Qiao","raw_affiliation_strings":["Snowflake, Bellevue, USA"],"raw_orcid":"https://orcid.org/0009-0004-9119-8696","affiliations":[{"raw_affiliation_string":"Snowflake, Bellevue, USA","institution_ids":["https://openalex.org/I4210108985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110772060","display_name":"Michael Wyatt","orcid":"https://orcid.org/0009-0008-8157-7667"},"institutions":[{"id":"https://openalex.org/I18332796","display_name":"Snow College","ror":"https://ror.org/04azdj983","country_code":"US","type":"education","lineage":["https://openalex.org/I18332796"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Wyatt","raw_affiliation_strings":["Snowflake, Menlo Park, USA"],"raw_orcid":"https://orcid.org/0000-0003-2860-6859","affiliations":[{"raw_affiliation_string":"Snowflake, Menlo Park, USA","institution_ids":["https://openalex.org/I18332796"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037534081","display_name":"Jeff Rasley","orcid":null},"institutions":[{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeff Rasley","raw_affiliation_strings":["Snowflake, Bellevue, USA"],"raw_orcid":"https://orcid.org/0000-0003-2153-0409","affiliations":[{"raw_affiliation_string":"Snowflake, Bellevue, USA","institution_ids":["https://openalex.org/I4210108985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040302174","display_name":"Yuxiong He","orcid":"https://orcid.org/0000-0003-0478-8854"},"institutions":[{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuxiong He","raw_affiliation_strings":["Snowflake, Bellevue, USA"],"raw_orcid":"https://orcid.org/0000-0003-0478-8854","affiliations":[{"raw_affiliation_string":"Snowflake, Bellevue, USA","institution_ids":["https://openalex.org/I4210108985"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069595628","display_name":"Samyam Rajbhandari","orcid":"https://orcid.org/0000-0002-0386-8759"},"institutions":[{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Samyam Rajbhandari","raw_affiliation_strings":["Snowflake, Bellevue, USA"],"raw_orcid":"https://orcid.org/0000-0002-0386-8759","affiliations":[{"raw_affiliation_string":"Snowflake, Bellevue, USA","institution_ids":["https://openalex.org/I4210108985"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.30039899,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1749","last_page":"1763"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.18799999356269836,"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/T12127","display_name":"Software System Performance and Reliability","score":0.18799999356269836,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.18729999661445618,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.0908999964594841,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.3666999936103821},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.2955000102519989},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.28380000591278076},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.260699987411499}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6251999735832214},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.423799991607666},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.3666999936103821},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3562000095844269},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2955000102519989},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.28380000591278076},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2644999921321869},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.26409998536109924},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.260699987411499},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.24809999763965607}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3779212.3790219","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3779212.3790219","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3779212.3790219","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3779212.3790219","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W4389518760","https://openalex.org/W4402671013","https://openalex.org/W4416035509"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-12T00:00:00"}
