<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<oembed>
  <author_name>inarizuuuushi</author_name>
  <author_url>https://blog.hatena.ne.jp/inarizuuuushi/</author_url>
  <blog_title>Sabrou-mal サブロウ丸</blog_title>
  <blog_url>https://inarizuuuushi.hatenablog.com/</blog_url>
  <categories>
    <anon>論文サーベイ</anon>
    <anon>分散深層学習</anon>
  </categories>
  <description>@article{shoeybi2019megatron, title={Megatron-lm: Training multi-billion parameter language models using model parallelism}, author={Shoeybi, Mohammad and Patwary, Mostofa and Puri, Raul and LeGresley, Patrick and Casper, Jared and Catanzaro, Bryan}, journal={arXiv preprint arXiv:1909.08053}, year={…</description>
  <height>190</height>
  <html>&lt;iframe src=&quot;https://hatenablog-parts.com/embed?url=https%3A%2F%2Finarizuuuushi.hatenablog.com%2Fentry%2F2022%2F06%2F08%2F090000&quot; title=&quot;サーベイ: Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism - Sabrou-mal サブロウ丸&quot; class=&quot;embed-card embed-blogcard&quot; scrolling=&quot;no&quot; frameborder=&quot;0&quot; style=&quot;display: block; width: 100%; height: 190px; max-width: 500px; margin: 10px 0px;&quot;&gt;&lt;/iframe&gt;</html>
  <image_url>https://cdn-ak.f.st-hatena.com/images/fotolife/i/inarizuuuushi/20220531/20220531180951.jpg</image_url>
  <provider_name>Hatena Blog</provider_name>
  <provider_url>https://hatena.blog</provider_url>
  <published>2022-06-08 09:00:00</published>
  <title>サーベイ: Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism</title>
  <type>rich</type>
  <url>https://inarizuuuushi.hatenablog.com/entry/2022/06/08/090000</url>
  <version>1.0</version>
  <width>100%</width>
</oembed>
