<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"
	xmlns:content="http://purl.org/rss/1.0/modules/content/"
	xmlns:wfw="http://wellformedweb.org/CommentAPI/"
	xmlns:dc="http://purl.org/dc/elements/1.1/"
	xmlns:atom="http://www.w3.org/2005/Atom"
	xmlns:sy="http://purl.org/rss/1.0/modules/syndication/"
	xmlns:slash="http://purl.org/rss/1.0/modules/slash/"
	>

<channel>
	<title>Quantization &#8211; Noise</title>
	<atom:link href="https://noise.getoto.net/tag/quantization/feed/" rel="self" type="application/rss+xml" />
	<link>https://noise.getoto.net</link>
	<description>The collective thoughts of the interwebz</description>
	<lastBuildDate>Mon, 03 Aug 2026 13:00:00 +0000</lastBuildDate>
	<language>en-US</language>
	<sy:updatePeriod>
	hourly	</sy:updatePeriod>
	<sy:updateFrequency>
	1	</sy:updateFrequency>
	<generator>https://wordpress.org/?v=7.1.3</generator>
	<item>
		<title>Smaller, faster, safer: running Kimi and GLM at scale</title>
		<link>https://noise.getoto.net/2026/08/03/smaller-faster-safer-running-kimi-and-glm-at-scale/</link>
		
		<dc:creator><![CDATA[Alex Reneau]]></dc:creator>
		<pubDate>Mon, 03 Aug 2026 13:00:00 +0000</pubDate>
				<category><![CDATA[Agents Week]]></category>
		<category><![CDATA[AI]]></category>
		<category><![CDATA[Developers]]></category>
		<category><![CDATA[inference]]></category>
		<category><![CDATA[Quantization]]></category>
		<category><![CDATA[Workers AI]]></category>
		<guid isPermaLink="false">http://noise.getoto.net/?guid=abe0935b3c6c3f3195a4f9b5dfc18069</guid>

					<description><![CDATA[Serving frontier models like Kimi and GLM means fighting for GPU memory. Here's how we quantize KV caches, compress model weights, and add integrity checks to serve them faster, cheaper, and safely.]]></description>
		
		
		<enclosure url="" length="0" type="" />

			</item>
	</channel>
</rss>

<!--
Performance optimized by W3 Total Cache. Learn more: https://www.boldgrid.com/w3-total-cache/?utm_source=w3tc&utm_medium=footer_comment&utm_campaign=free_plugin

Object Caching 20/27 objects using Memcached
Page Caching using Disk: Enhanced 
Lazy Loading (feed)
Database Caching using Memcached

Served from: noise.getoto.net @ 2026-10-24 21:40:59 by W3 Total Cache
-->