<?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>Quantization on Sandeep Kumar</title><link>https://sandeep007734.github.io/tags/quantization/</link><description>Recent content in Quantization on Sandeep Kumar</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Wed, 12 Aug 2026 00:00:00 +0530</lastBuildDate><atom:link href="https://sandeep007734.github.io/tags/quantization/feed.xml" rel="self" type="application/rss+xml"/><item><title>Neural Network Quantization</title><link>https://sandeep007734.github.io/posts/nn_quantization/</link><pubDate>Wed, 12 Aug 2026 00:00:00 +0530</pubDate><guid>https://sandeep007734.github.io/posts/nn_quantization/</guid><description>The affine quantization map, per-tensor against per-channel scaling, post-training quantization versus quantization-aware training, why activation outliers make transformers hard to quantize, and the methods that recover the lost accuracy.</description></item></channel></rss>