Posts by Lorri Rao

Implementing a High-Performance Custom Diffusion Attention Kernel with FlyDSL

Readers may be familiar with traditional Transformer models and their attention mechanisms. The traditional autoregressive transformers generate tokens iteratively. Since this feature significantly limits the inference throughput, researchers have begun exploring approaches such as diffusion models that can generate multiple tokens in each iteration.

Read more ...


Optimizing LLM Workloads: AMD Instinct MI355X GPUs Drive Competitive Performance

AI training workloads are pushing the limits of modern GPU architectures. With the release of AMD ROCm™ 7.0 software, AMD is raising the bar for high-performance training by delivering optimized support for LLM workloads across the JAX and PyTorch frameworks. The latest v25.9 Training Dockers demonstrate exceptional scaling efficiency for both single-node and multi-node setups, empowering researchers and developers to push model sizes and complexity further than ever.

Read more ...