<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>About this handbook on AI Tools</title>
    <link>https://ait.bsc.es/handbook/introduction/</link>
    <description>Recent content in About this handbook on AI Tools</description>
    <generator>Hugo</generator>
    <language>en</language>
    <atom:link href="https://ait.bsc.es/handbook/introduction/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Introduction</title>
      <link>https://ait.bsc.es/handbook/introduction/introduction/</link>
      <pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate>
      <guid>https://ait.bsc.es/handbook/introduction/introduction/</guid>
      <description>&lt;p&gt;Serving a large language model in production is a different discipline from training&#xA;one. The model is fixed, the traffic is not, and the work shifts to latency budgets,&#xA;memory limits, batching behaviour and the operational question of keeping expensive&#xA;accelerators busy without breaking service-level objectives.&lt;/p&gt;&#xA;&lt;p&gt;This handbook collects what the AI Tools team has learned doing that work. It is&#xA;organised as a path: foundations first, then planning a deployment, preparing a model,&#xA;interacting with it, optimizing throughput and latency, and finally the infrastructure&#xA;and operations that keep a service running.&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
