Posts by Sopiko Kurdadze
Training AI Weather Forecasting Models on AMD Instinct
- 10 November 2025
Weather forecasting is one of the most computationally intensive scientific challenges and an essential societal need. Predicting extreme weather events, agricultural and energy planning and daily forecasts all require accurate weather predictions. Traditionally, Numerical Weather Prediction (NWP) has served as the foundation of weather forecasting by solving complex physical equations that require significant computational power. However, recent advances in machine learning have led to the development of alternative prediction models that reduce computational costs by orders of magnitude, while either maintaining or improving accuracy in forecasts. Models like GenCast [1], Pangu-Weather [2], Aurora [3] and others have shown promising results in this area (see the WeatherBench [4] scorecard). Running inference on these models using AMD GPUs is straightforward, as highlighted in our recent blog post: Running SOTA AI-based Weather Forecasting models on AMD Instinct.
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.
Accelerating FastVideo on AMD GPUs with TeaCache
- 19 August 2025
Video generation is entering a new era, powered by diffusion models that deliver photorealistic and temporally consistent results from text prompts. Models like Wan2.1 push the boundaries of what’s possible in AI-generated content, but to unlock their full potential, inference performance must scale with both model complexity and hardware capabilities.