<?xml version="1.0" encoding="UTF-8"?><rss xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:atom="http://www.w3.org/2005/Atom" version="2.0"><channel><title><![CDATA[找到个蛮有用的用3090部署本地模型的repo]]></title><description><![CDATA[<p dir="auto"><a href="https://github.com/noonghunna/club-3090" rel="nofollow ugc">https://github.com/noonghunna/club-3090</a></p>
<p dir="auto">这个repo跟新得蛮快的，最近在用dflash</p>
<p dir="auto">bash scripts/launch.sh --variant beellama/dflash</p>
<p dir="auto">准备过两天在进一张3090跑双卡，这个repo也有支持</p>
]]></description><link>https://lcz.me/topic/417/找到个蛮有用的用3090部署本地模型的repo</link><generator>RSS for Node</generator><lastBuildDate>Sat, 06 Jun 2026 03:31:32 GMT</lastBuildDate><atom:link href="https://lcz.me/topic/417.rss" rel="self" type="application/rss+xml"/><pubDate>Thu, 04 Jun 2026 02:02:30 GMT</pubDate><ttl>60</ttl><item><title><![CDATA[Reply to 找到个蛮有用的用3090部署本地模型的repo on Fri, 05 Jun 2026 08:58:18 GMT]]></title><description><![CDATA[<p dir="auto">非常好，感谢分享。可以到这里来看下帖子：<br />
<a href="https://lcz.me/topic/398/%E8%AB%96-a10g-3090-%E5%BA%95%E4%B8%8B%E7%9A%84gemma-4%E8%B7%9Fqwen-3.6%E6%B8%AC%E8%A9%A6%E5%BF%83%E5%BE%97/16">https://lcz.me/topic/398/論-a10g-3090-底下的gemma-4跟qwen-3.6測試心得/16</a></p>
]]></description><link>https://lcz.me/post/5183</link><guid isPermaLink="true">https://lcz.me/post/5183</guid><dc:creator><![CDATA[terry]]></dc:creator><pubDate>Fri, 05 Jun 2026 08:58:18 GMT</pubDate></item><item><title><![CDATA[Reply to 找到个蛮有用的用3090部署本地模型的repo on Thu, 04 Jun 2026 02:11:01 GMT]]></title><description><![CDATA[<p dir="auto">這個我設立A10G的帖子也有參考過, 但是有部分設定不能直接拿來用,</p>
<p dir="auto">int8_per_token_head的KV Cache就是其中一個, 不過它的數值參數有寫解釋而不是硬塞, 很有參考價值</p>
]]></description><link>https://lcz.me/post/4923</link><guid isPermaLink="true">https://lcz.me/post/4923</guid><dc:creator><![CDATA[566656661]]></dc:creator><pubDate>Thu, 04 Jun 2026 02:11:01 GMT</pubDate></item></channel></rss>