<?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>Integer-Inference on 3rd layer</title><link>https://3rdlayer.uk/tags/integer-inference/</link><description>Recent content in Integer-Inference on 3rd layer</description><generator>Hugo -- 0.154.5</generator><language>en-US</language><lastBuildDate>Sat, 09 May 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://3rdlayer.uk/tags/integer-inference/index.xml" rel="self" type="application/rss+xml"/><item><title>Integer-Arithmetic-Only Neural Network Inference — Linear Quantization</title><link>https://3rdlayer.uk/posts/linear-quantization/</link><pubDate>Sat, 09 May 2026 00:00:00 +0000</pubDate><guid>https://3rdlayer.uk/posts/linear-quantization/</guid><description>Beyond storing weights as integers — running the multiplications and additions entirely in integer arithmetic at inference. We connect reals and integers with the affine map r = S(q − Z), and explore it with a widget where you change the scale and zero point and watch the quantization error. (Jacob et al. 2018, the basis of TFLite integer quantization)</description></item></channel></rss>