DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inference.
Resource URI: https://dblp.l3s.de/d2r/resource/publications/journals/corr/abs-2401-08671
Home
|
Example Publications
Property
Value
dcterms:
bibliographicCitation
<
http://dblp.uni-trier.de/rec/bibtex/journals/corr/abs-2401-08671
>
dc:
creator
<
https://dblp.l3s.de/d2r/resource/authors/Ammar_Ahmad_Awan
>
dc:
creator
<
https://dblp.l3s.de/d2r/resource/authors/Arash_Bakhtiari
>
dc:
creator
<
https://dblp.l3s.de/d2r/resource/authors/Connor_Holmes
>
dc:
creator
<
https://dblp.l3s.de/d2r/resource/authors/Heyang_Qin
>
dc:
creator
<
https://dblp.l3s.de/d2r/resource/authors/Jeff_Rasley
>
dc:
creator
<
https://dblp.l3s.de/d2r/resource/authors/Lev_Kurilenko
>
dc:
creator
<
https://dblp.l3s.de/d2r/resource/authors/Masahiro_Tanaka
>
dc:
creator
<
https://dblp.l3s.de/d2r/resource/authors/Michael_Wyatt
>
dc:
creator
<
https://dblp.l3s.de/d2r/resource/authors/Reza_Yazdani_Aminabadi
>
dc:
creator
<
https://dblp.l3s.de/d2r/resource/authors/Samyam_Rajbhandari
>
dc:
creator
<
https://dblp.l3s.de/d2r/resource/authors/Yuxiong_He
>
foaf:
homepage
<
http://dx.doi.org/doi.org%2F10.48550%2FarXiv.2401.08671
>
foaf:
homepage
<
https://doi.org/10.48550/arXiv.2401.08671
>
dc:
identifier
DBLP journals/corr/abs-2401-08671
(xsd:string)
dc:
identifier
DOI doi.org%2F10.48550%2FarXiv.2401.08671
(xsd:string)
dcterms:
issued
2024
(xsd:gYear)
swrc:
journal
<
https://dblp.l3s.de/d2r/resource/journals/corr
>
rdfs:
label
DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inference.
(xsd:string)
foaf:
maker
<
https://dblp.l3s.de/d2r/resource/authors/Ammar_Ahmad_Awan
>
foaf:
maker
<
https://dblp.l3s.de/d2r/resource/authors/Arash_Bakhtiari
>
foaf:
maker
<
https://dblp.l3s.de/d2r/resource/authors/Connor_Holmes
>
foaf:
maker
<
https://dblp.l3s.de/d2r/resource/authors/Heyang_Qin
>
foaf:
maker
<
https://dblp.l3s.de/d2r/resource/authors/Jeff_Rasley
>
foaf:
maker
<
https://dblp.l3s.de/d2r/resource/authors/Lev_Kurilenko
>
foaf:
maker
<
https://dblp.l3s.de/d2r/resource/authors/Masahiro_Tanaka
>
foaf:
maker
<
https://dblp.l3s.de/d2r/resource/authors/Michael_Wyatt
>
foaf:
maker
<
https://dblp.l3s.de/d2r/resource/authors/Reza_Yazdani_Aminabadi
>
foaf:
maker
<
https://dblp.l3s.de/d2r/resource/authors/Samyam_Rajbhandari
>
foaf:
maker
<
https://dblp.l3s.de/d2r/resource/authors/Yuxiong_He
>
owl:
sameAs
<
http://bibsonomy.org/uri/bibtexkey/journals/corr/abs-2401-08671/dblp
>
owl:
sameAs
<
http://dblp.rkbexplorer.com/id/journals/corr/abs-2401-08671
>
rdfs:
seeAlso
<
http://dblp.uni-trier.de/db/journals/corr/corr2401.html#abs-2401-08671
>
rdfs:
seeAlso
<
https://doi.org/10.48550/arXiv.2401.08671
>
dc:
title
DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inference.
(xsd:string)
dc:
type
<
http://purl.org/dc/dcmitype/Text
>
rdf:
type
swrc:Article
rdf:
type
foaf:Document
swrc:
volume
abs/2401.08671
(xsd:string)