<?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>Prompt Lookup Drafting on Negi AI Lab</title><link>https://ai.negi-lab.com/tags/prompt-lookup-drafting/</link><description>Recent content in Prompt Lookup Drafting on Negi AI Lab</description><image><title>Negi AI Lab</title><url>https://ai.negi-lab.com/images/og-default.png</url><link>https://ai.negi-lab.com/images/og-default.png</link></image><generator>Hugo -- 0.154.5</generator><language>ja</language><lastBuildDate>Fri, 02 Oct 2026 04:47:10 +0900</lastBuildDate><atom:link href="https://ai.negi-lab.com/tags/prompt-lookup-drafting/index.xml" rel="self" type="application/rss+xml"/><item><title>ローカルLLMが爆速に。llama.cppの新機能をフル活用するRTX・Macの選び方と比較</title><link>https://ai.negi-lab.com/posts/llamacpp-prompt-lookup-drafting-gpu-guide/</link><pubDate>Fri, 02 Oct 2026 00:00:00 +0900</pubDate><guid>https://ai.negi-lab.com/posts/llamacpp-prompt-lookup-drafting-gpu-guide/</guid><description>llama.cppの「Prompt Lookup Drafting（PLD）」により、コード生成やRAGなど特定の用途で推論速度が最大42倍（実効2〜5倍...</description></item></channel></rss>