<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>performance on Margin Notes</title><link>https://www.191196.xyz/tags/performance/</link><description>Recent content in performance on Margin Notes</description><generator>Hugo</generator><language>en-US</language><lastBuildDate>Fri, 30 Oct 2026 09:26:00 +0000</lastBuildDate><atom:link href="https://www.191196.xyz/tags/performance/index.xml" rel="self" type="application/rss+xml"/><item><title>Three papers I keep re-reading about inference cost</title><link>https://www.191196.xyz/posts/inference-papers/</link><pubDate>Fri, 30 Oct 2026 09:26:00 +0000</pubDate><guid>https://www.191196.xyz/posts/inference-papers/</guid><description>Paged attention, speculative decoding, and 4-bit weights — what each one actually buys.</description></item><item><title>When a Postgres index made the query slower</title><link>https://www.191196.xyz/posts/postgres-index/</link><pubDate>Sat, 12 Apr 2025 19:05:00 +0000</pubDate><guid>https://www.191196.xyz/posts/postgres-index/</guid><description>A composite index looked like the obvious fix. It made p99 four times worse for a week before I noticed.</description></item></channel></rss>