<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>AI 技術 on 筆墨碎語｜RxChi1d</title><link>https://inktrace.rxchi1d.me/categories/ai-technical/</link><description>Recent content in AI 技術 on 筆墨碎語｜RxChi1d</description><generator>Hugo -- gohugo.io</generator><language>zh-tw</language><managingEditor>rchildlin@gmail.com (RxChi1d)</managingEditor><webMaster>rchildlin@gmail.com (RxChi1d)</webMaster><copyright>© 2026 RxChi1d</copyright><lastBuildDate>Sat, 11 Jul 2026 02:07:20 +0800</lastBuildDate><atom:link href="https://inktrace.rxchi1d.me/categories/ai-technical/index.xml" rel="self" type="application/rss+xml"/><item><title>幫 Ornith-1.0-35B 移植 MTP：從 GGUF 手術到 Hermes Agent 接入</title><link>https://inktrace.rxchi1d.me/posts/ai-technical/ornith-1-0-35b-mtp-deployment-notes/</link><pubDate>Mon, 06 Jul 2026 21:15:09 +0800</pubDate><author>rchildlin@gmail.com (RxChi1d)</author><guid>https://inktrace.rxchi1d.me/posts/ai-technical/ornith-1-0-35b-mtp-deployment-notes/</guid><description>&lt;p&gt;本文帶你用 llama.cpp 在本地端部署 Ornith-1.0-35B、接入 Hermes Agent，最後再透過移植 MTP head 進一步提升推理速度。&lt;/p&gt;</description></item><item><title>使用 Fish Speech S2-Pro 架設本地 TTS 服務</title><link>https://inktrace.rxchi1d.me/posts/ai-technical/fish-speech-local-tts/</link><pubDate>Tue, 30 Jun 2026 00:28:34 +0800</pubDate><author>rchildlin@gmail.com (RxChi1d)</author><guid>https://inktrace.rxchi1d.me/posts/ai-technical/fish-speech-local-tts/</guid><description>&lt;p&gt;Fish Speech S2-Pro 是 Fish Audio 的 SOTA 開源 TTS 模型。本文記錄如何將它部署到 RTX 3090（24 GB VRAM）上，並整合進 Hermes Agent，打造一個完全 local、低延遲的語音合成服務。&lt;/p&gt;</description></item></channel></rss>