<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Custom Models on AI VOID</title><link>https://ai-blog.noorshomelab.dev/tags/custom-models/</link><description>Recent content in Custom Models on AI VOID</description><generator>Hugo</generator><language>en</language><lastBuildDate>Sun, 26 Oct 2025 00:00:00 +0000</lastBuildDate><atom:link href="https://ai-blog.noorshomelab.dev/tags/custom-models/index.xml" rel="self" type="application/rss+xml"/><item><title>Advanced Topics: WebGPU, Quantization, and Custom Models</title><link>https://ai-blog.noorshomelab.dev/transformers-js-guide/advanced-topics-webgpu-quantization-and-custom-models/</link><pubDate>Sun, 26 Oct 2025 00:00:00 +0000</pubDate><guid>https://ai-blog.noorshomelab.dev/transformers-js-guide/advanced-topics-webgpu-quantization-and-custom-models/</guid><description>&lt;h1 id="6-advanced-topics-webgpu-quantization-and-custom-models"&gt;6. Advanced Topics: WebGPU, Quantization, and Custom Models&lt;/h1&gt;
&lt;p&gt;Having covered the fundamental and intermediate tasks, let&amp;rsquo;s dive into more advanced aspects of Transformers.js that are crucial for optimizing performance, managing resources, and extending its capabilities.&lt;/p&gt;
&lt;h2 id="61-leveraging-webgpu-for-performance"&gt;6.1. Leveraging WebGPU for Performance&lt;/h2&gt;
&lt;p&gt;WebGPU is a new web standard for accelerated graphics and compute, offering significant performance gains over WebGL and WebAssembly (WASM) for machine learning workloads. Transformers.js v3 fully embraces WebGPU, allowing you to run models directly on the user&amp;rsquo;s GPU from the browser.&lt;/p&gt;</description></item></channel></rss>