<?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>CPU Inference on Enrico Pesce</title><link>https://www.enricopesce.it/tags/cpu-inference/</link><description>Recent content in CPU Inference on Enrico Pesce</description><generator>Hugo</generator><language>en-US</language><copyright>Enrico Pesce</copyright><lastBuildDate>Wed, 04 Feb 2026 09:00:00 +0100</lastBuildDate><atom:link href="https://www.enricopesce.it/tags/cpu-inference/index.xml" rel="self" type="application/rss+xml"/><item><title>Generative AI: Efficient Inference on Cloud CPUs</title><link>https://www.enricopesce.it/generative-ai-efficient-inference-on-cloud-cpus/</link><pubDate>Wed, 04 Feb 2026 09:00:00 +0100</pubDate><guid>https://www.enricopesce.it/generative-ai-efficient-inference-on-cloud-cpus/</guid><description>Real benchmarks showing how optimized CPU inference on Ampere processors delivers production-ready performance without GPUs.</description></item></channel></rss>