{"id":31321,"date":"2025-03-22T17:08:15","date_gmt":"2025-03-22T09:08:15","guid":{"rendered":"https:\/\/www.1ai.net\/?p=31321"},"modified":"2025-03-22T17:08:15","modified_gmt":"2025-03-22T09:08:15","slug":"amd-%e6%8e%a8%e5%87%ba%e5%bc%80%e6%ba%90%e9%a1%b9%e7%9b%aegaia%e5%ae%9e%e7%8e%b0%e6%9c%ac%e5%9c%b0%e5%a4%a7%e6%a8%a1%e5%9e%8b%e9%ab%98%e6%95%88%e8%bf%90%e8%a1%8c%ef%bc%9a%e9%92%88","status":"publish","type":"post","link":"https:\/\/www.1ai.net\/en\/31321.html","title":{"rendered":"AMD Launches Open Source Project \"GAIA\" to Enable Efficient Running of Native Large Models: Optimized for Raider AI 300 Series Processors, Currently Available Only for Windows"},"content":{"rendered":"

March 22 - Thursday, local time.AMD<\/a> Announcing the launch of applications designed to run locally on the Large Language Model (LLM)\u00a0GAIA<\/a>(pronounced \/\u02c8\u0261a\u026a.\u0259\/) and is open-sourced on Github, and is currently limited to the Windows platform.<\/p>\n

\"2ec586c2j00stipci00igd000v900hkp\"<\/p>\n

GAIA is a generative AI application that enables localized private running of LLMs on Windows PCs and is optimized for the Rui Long AI 300 series processors, marking another important placement of AMD in the edge computing space.<\/p>\n

Running GAIA on the NPU improves performance on AI-specific tasks. Starting with Ryzen AI software version 1.3, there is hybrid support for deploying quantized LLMs that use both the NPU and core graphics.<\/p>\n

Its core components are developed based on ONNX TurnkeyML's Lemonade SDK, and it adopts the Retrieval Augmented Generation (RAG) technology framework, which realizes real-time retrieval and analysis of external data such as YouTube, GitHub, and so on through local vector indexes.<\/p>\n

The system workflow contains three modules: LLM Connector, LlamaIndex RAG Pipeline, and Agent Web Server, which support mainstream models such as Llama and Phi. The function module contains four major AI intelligences:<\/p>\n