Posts by Grant Pinkert
From Vector Search to Agentic RAG: Building an Enterprise Research Analyst with hipVS
- 15 July 2026
hipVS and hipRAFT were introduced in this earlier blog post, which walked through the core vector search APIs. This post takes the next step: it shows what you can build with hipVS by walking through an Enterprise Research Analyst demo — an end-to-end working agentic RAG (Retrieval-Augmented Generation) system that uses hipVS as its retrieval backbone. This demo combines multi-document ingestion, LLM-powered query decomposition, parallel GPU-accelerated vector search, and cross-document synthesis with source citations, all running on AMD hardware. Along the way, it highlights the specific hipVS and hipRAFT APIs the demo exercises and shares code snippets you can adapt for your own applications.
Plug-and-Play CuPy on ROCm: Data Analytics Acceleration Made Simple
- 14 November 2025
AMD is committed to ensuring that CuPy works seamlessly on AMD Instinct GPUs through ROCm and has worked to support the latest features in upstream CuPy on ROCm. In this blog, you will learn about the enhancements in the current and upcoming AMD CuPy releases that will supercharge your analytics and data science projects. In an earlier blog on CuPy and hipDF, it was demonstrated that CuPy and hipDF can be applied to complex analytics tasks with large datasets on ROCm using AMD GPUs. That blog used a PyPI wheel forked from earlier versions of CuPy and cuDF, and both CuPy and ROCm have advanced since then. In the latest AMD CuPy release, you will find many exciting improvements from the upstream CuPy library as well as ROCm 7.