Efficient Memory Management for Large Language Model Serving with PagedAttention.
Resource URI: https://dblp.l3s.de/d2r/resource/publications/conf/sosp/KwonLZ0ZY0ZS23
Home
|
Example Publications
Property
Value
dcterms:
bibliographicCitation
<
http://dblp.uni-trier.de/rec/bibtex/conf/sosp/KwonLZ0ZY0ZS23
>
dc:
creator
<
https://dblp.l3s.de/d2r/resource/authors/Cody_Hao_Yu
>
dc:
creator
<
https://dblp.l3s.de/d2r/resource/authors/Hao_Zhang
>
dc:
creator
<
https://dblp.l3s.de/d2r/resource/authors/Ion_Stoica
>
dc:
creator
<
https://dblp.l3s.de/d2r/resource/authors/Joseph_Gonzalez_0001
>
dc:
creator
<
https://dblp.l3s.de/d2r/resource/authors/Lianmin_Zheng
>
dc:
creator
<
https://dblp.l3s.de/d2r/resource/authors/Siyuan_Zhuang
>
dc:
creator
<
https://dblp.l3s.de/d2r/resource/authors/Woosuk_Kwon
>
dc:
creator
<
https://dblp.l3s.de/d2r/resource/authors/Ying_Sheng_0007
>
dc:
creator
<
https://dblp.l3s.de/d2r/resource/authors/Zhuohan_Li_0001
>
foaf:
homepage
<
http://dx.doi.org/doi.org%2F10.1145%2F3600006.3613165
>
foaf:
homepage
<
https://doi.org/10.1145/3600006.3613165
>
dc:
identifier
DBLP conf/sosp/KwonLZ0ZY0ZS23
(xsd:string)
dc:
identifier
DOI doi.org%2F10.1145%2F3600006.3613165
(xsd:string)
dcterms:
issued
2023
(xsd:gYear)
rdfs:
label
Efficient Memory Management for Large Language Model Serving with PagedAttention.
(xsd:string)
foaf:
maker
<
https://dblp.l3s.de/d2r/resource/authors/Cody_Hao_Yu
>
foaf:
maker
<
https://dblp.l3s.de/d2r/resource/authors/Hao_Zhang
>
foaf:
maker
<
https://dblp.l3s.de/d2r/resource/authors/Ion_Stoica
>
foaf:
maker
<
https://dblp.l3s.de/d2r/resource/authors/Joseph_Gonzalez_0001
>
foaf:
maker
<
https://dblp.l3s.de/d2r/resource/authors/Lianmin_Zheng
>
foaf:
maker
<
https://dblp.l3s.de/d2r/resource/authors/Siyuan_Zhuang
>
foaf:
maker
<
https://dblp.l3s.de/d2r/resource/authors/Woosuk_Kwon
>
foaf:
maker
<
https://dblp.l3s.de/d2r/resource/authors/Ying_Sheng_0007
>
foaf:
maker
<
https://dblp.l3s.de/d2r/resource/authors/Zhuohan_Li_0001
>
swrc:
pages
611-626
(xsd:string)
dcterms:
partOf
<
https://dblp.l3s.de/d2r/resource/publications/conf/sosp/2023
>
owl:
sameAs
<
http://bibsonomy.org/uri/bibtexkey/conf/sosp/KwonLZ0ZY0ZS23/dblp
>
owl:
sameAs
<
http://dblp.rkbexplorer.com/id/conf/sosp/KwonLZ0ZY0ZS23
>
rdfs:
seeAlso
<
http://dblp.uni-trier.de/db/conf/sosp/sosp2023.html#KwonLZ0ZY0ZS23
>
rdfs:
seeAlso
<
https://doi.org/10.1145/3600006.3613165
>
swrc:
series
<
https://dblp.l3s.de/d2r/resource/conferences/sosp
>
dc:
title
Efficient Memory Management for Large Language Model Serving with PagedAttention.
(xsd:string)
dc:
type
<
http://purl.org/dc/dcmitype/Text
>
rdf:
type
swrc:InProceedings
rdf:
type
foaf:Document