<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Run:ai on Antoine Boucher</title><link>https://antoineboucher.info/CV/blog/tags/runai/</link><description>Recent content in Run:ai on Antoine Boucher</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Tue, 06 Sep 2022 10:00:00 -0400</lastBuildDate><atom:link href="https://antoineboucher.info/CV/blog/tags/runai/index.xml" rel="self" type="application/rss+xml"/><item><title>Run:ai on AWS — webinar notes (inference &amp; autoscaling)</title><link>https://antoineboucher.info/CV/blog/posts/runai-aws-inference-webinar/</link><pubDate>Tue, 06 Sep 2022 10:00:00 -0400</pubDate><guid>https://antoineboucher.info/CV/blog/posts/runai-aws-inference-webinar/</guid><description>&lt;p&gt;Notes from the &lt;strong&gt;Run:ai&lt;/strong&gt; webinar on running and scaling &lt;strong&gt;inference&lt;/strong&gt; workloads on &lt;strong&gt;AWS&lt;/strong&gt; (Americas). Run:ai focuses on scheduling, visibility, and efficiency for GPU-backed models in shared environments.&lt;/p&gt;
&lt;h2 id="dashboard"&gt;Dashboard&lt;/h2&gt;
&lt;p&gt;Overview of jobs and resource usage.&lt;/p&gt;
&lt;p&gt;&lt;img src="https://antoineboucher.info/CV/blog/posts/runai-aws-inference-webinar/images/dashboard.jpeg" alt="Dashboard"&gt;&lt;/p&gt;
&lt;p&gt;&lt;img src="https://antoineboucher.info/CV/blog/posts/runai-aws-inference-webinar/images/dashboard1.jpeg" alt="Dashboard (alternate view)"&gt;&lt;/p&gt;
&lt;h2 id="cli"&gt;CLI&lt;/h2&gt;
&lt;p&gt;Command-line operations and automation.&lt;/p&gt;
&lt;p&gt;&lt;img src="https://antoineboucher.info/CV/blog/posts/runai-aws-inference-webinar/images/cli.jpeg" alt="CLI"&gt;&lt;/p&gt;
&lt;h2 id="models-and-load"&gt;Models and load&lt;/h2&gt;
&lt;p&gt;&lt;img src="https://antoineboucher.info/CV/blog/posts/runai-aws-inference-webinar/images/model.jpeg" alt="Model view"&gt;&lt;/p&gt;
&lt;p&gt;&lt;img src="https://antoineboucher.info/CV/blog/posts/runai-aws-inference-webinar/images/multi.jpeg" alt="Multi-instance / scaling"&gt;&lt;/p&gt;
&lt;h2 id="workload-management"&gt;Workload management&lt;/h2&gt;
&lt;p&gt;&lt;img src="https://antoineboucher.info/CV/blog/posts/runai-aws-inference-webinar/images/managing.jpeg" alt="Managing workloads"&gt;&lt;/p&gt;
&lt;h2 id="infrastructure-view"&gt;Infrastructure view&lt;/h2&gt;
&lt;p&gt;&lt;img src="https://antoineboucher.info/CV/blog/posts/runai-aws-inference-webinar/images/servers.jpeg" alt="Servers"&gt;&lt;/p&gt;
&lt;h2 id="demo"&gt;Demo&lt;/h2&gt;
&lt;p&gt;&lt;img src="https://antoineboucher.info/CV/blog/posts/runai-aws-inference-webinar/images/demo.jpeg" alt="Demo"&gt;&lt;/p&gt;
&lt;h2 id="challenges"&gt;Challenges&lt;/h2&gt;
&lt;p&gt;&lt;img src="https://antoineboucher.info/CV/blog/posts/runai-aws-inference-webinar/images/challenges.jpeg" alt="Challenges slide"&gt;&lt;/p&gt;
&lt;hr&gt;
&lt;p&gt;For product details, see the official &lt;strong&gt;Run:ai&lt;/strong&gt; documentation and &lt;strong&gt;AWS&lt;/strong&gt; marketplace or partner listings.&lt;/p&gt;</description></item></channel></rss>