0

Reza Yazdani Aminabadi

Papers
1

Cite

Notes

Only stored in your browser.

Attribution

Affiliations & profile
Semantic Scholar
Attribution policy →
1papers

Authored papers

1

DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inference

arXiv 2024

2024

Affiliations

No known affiliations.

Frequent co-authors

10

from 1 papers

Ammar Ahmad Awan

1 shared paper

Arash Bakhtiari

1 shared paper

Connor Holmes

1 shared paper

Heyang Qin

1 shared paper

Jeff Rasley

1 shared paper

Lev Kurilenko

1 shared paper

Masahiro Tanaka

1 shared paper

Michael Wyatt

1 shared paper

Samyam Rajbhandari

1 shared paper

Yuxiong He

1 shared paper