Posts by Albin Toft
HPC Coding Agent - Part 1: Combining GLM-powered Cline and RAG Using MCP
- 03 December 2025
Navigating through extensive High Performance Computing (HPC) documentation can be challenging, especially when working with complex supercomputer environments like LUMI, one of the pan-European pre-exascale supercomputers. Traditional search methods often fall short when you need contextual, actionable answers to technical questions. RAG (Retrieval-Augmented Generation) agents offer a solution by combining large language model reasoning with domain-specific knowledge retrieval to provide accurate, cited responses to your HPC queries.
Using Reinforcement Learning to Fix Text in AI-Generated Videos
- 25 November 2025
One common giveaway that a video is AI-generated is the text. Letters may look slightly malformed or nonsensical, words can be misspelled and full sentences can have grammatical errors. Improving text generation in videos isn’t just a cosmetic issue - it is essential to generate the prompted text precisely, lest the message become confusing, unprofessional, and potentially misleading. This is an excellent case for leveraging reinforcement learning to improve a video generation model on a specific task without requiring massive amounts of suitable training data.
A Simple Design for Serving Video Generation Models with Distributed Inference
- 24 September 2025
Video generation is entering a new era, powered by diffusion models that deliver photorealistic and temporally consistent results from text prompts. Models like Wan2.2 push the boundaries of what’s possible in AI-generated content, but to make them practical, inference performance needs to scale in real-world terms: handling more simultaneous users, keeping response times reasonable, and efficiently using multiple GPUs or compute nodes.
Running ComfyUI on AMD Instinct
- 19 August 2025
Building workflows for generative AI tasks can of course be done purely in code. However, as the interest in GenAI has soared together with its use in people’s daily lives, more and more people start to search for and explore tools and software for building GenAI workflows that do not require extensive programming knowledge. One such tool is ComfyUI, which provides users with a simple drag and drop UI for building GenAI workflows. This blog post will briefly cover what ComfyUI is, and how you can get it up and running on your AMD Instinct hardware.