Posts by Johanna Yang

HPC Coding Agent - Part 1: Combining GLM-powered Cline and RAG Using MCP

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.

Read more ...


Exploring Gameplay Video Generation with Hunyuan-GameCraft

Video generation is progressing rapidly, with new models and techniques emerging frequently. This blog aims to explore these capabilities in the context of gameplay video generation. For this, we demonstrate how Hunyuan-GameCraft can be leveraged to generate gameplay video from a single image and user action input on AMD Instinct™ GPUs with ROCm.

Read more ...


Inference with HunyuanWorld-Voyager on AMD Instinct GPUs

Single-image 3D world generation faces several technical challenges: occluded regions are often hallucinated, depth consistency varies across frames, long camera trajectories introduce drift, and multi-stage pipelines (such as separate depth estimation and SfM/MVS) add latency while compounding errors. HunyuanWorld‑Voyager addresses these limitations through a world-consistent video diffusion model. Given a single image and an optional camera trajectory, it jointly generates RGB frames and per-frame aligned depth maps that follow the specified camera motion. A lightweight world cache enables geometric reprojection for improved occlusion handling and supports autoregressive extension for long or effectively unbounded explorations. The aligned depth outputs allow direct export to point clouds, Gaussian splats, or meshes without requiring a separate reconstruction stage.

Read more ...


Accelerating Audio-Driven Video Generation: WAN2.2-S2V on AMD ROCm

Audio-driven video generation is rapidly evolving, opening new possibilities for creative content and intelligent automation. In this blog, we showcase how AMD Instinct MI300X GPUs and the ROCm software stack empower cutting-edge models like Wan2.2-S2V to deliver high-quality, expressive character animation at scale.

Read more ...


All-in-One Video Editing with VACE on AMD Instinct GPUs

This blog takes a closer look at recent advances in AI-powered video editing, highlighting how modern diffusion models enable users to accomplish various video editing tasks on AMD Instinct GPUs using Alibaba’s VACE model.

Read more ...