<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Multi-GPU |</title><link>https://yzm1205.github.io/tags/multi-gpu/</link><atom:link href="https://yzm1205.github.io/tags/multi-gpu/index.xml" rel="self" type="application/rss+xml"/><description>Multi-GPU</description><generator>HugoBlox Kit (https://hugoblox.com)</generator><language>en-us</language><lastBuildDate>Wed, 01 Jan 2025 00:00:00 +0000</lastBuildDate><image><url>https://yzm1205.github.io/media/icon_hu_1c0e9cb08cfb822a.png</url><title>Multi-GPU</title><link>https://yzm1205.github.io/tags/multi-gpu/</link></image><item><title>Shard-Any-LLMs</title><link>https://yzm1205.github.io/projects/shard-any-llms/</link><pubDate>Wed, 01 Jan 2025 00:00:00 +0000</pubDate><guid>https://yzm1205.github.io/projects/shard-any-llms/</guid><description>&lt;p&gt;Selected research software.&lt;/p&gt;
&lt;ul&gt;
&lt;li&gt;Developed an automated model-sharding workflow for distributing large language models across
multiple GPUs, with command-line interfaces, Hugging Face integration, and environment-based
authentication.&lt;/li&gt;
&lt;/ul&gt;</description></item></channel></rss>