Posts by Emelie Wahlstrom
AIM: Unified User Experience from Profile Discovery to Deployment
- 30 September 2026
This post is a continuation of the Multi-Accelerator Support for AIMs and AMD Solution Blueprints blog, which introduced (i) multi-accelerator coverage across AMD Instinct™ GPUs, Radeon™ PRO GPUs, and EPYC™ CPUs, and (ii) walked through the Document Summarization Solution Blueprint. Here we focus on AIMs specifically and show how they deliver a unified user experience from Radeon to Instinct, i.e., similar profile discovery commands, container workflow, and OpenAI-compatible API regardless of the accelerator.
Retrieval Augmented Generation (RAG) with vLLM, LangChain and Chroma
- 04 November 2025
In this blog from the AMD Silo AI Programs, we build a simple Retrieval‑Augmented Generation (RAG) pipeline. While pretrained models are powerful, they lack access to proprietary or enterprise-specific knowledge. RAG closes that gap by retrieving relevant enterprise knowledge and injecting it into the prompt so the model can produce context‑aware answers. For enterprises, RAG systems offer an efficient way to query their knowledge bases and deliver relevant information to their users.