Researchers uncover side-channel attacks that target the GPU

'There's a tendency to say that all ML workloads need a GPU, but for inference you probably don't need them'

At the KubeCon event in Paris this week, Nvidia engineers spoke of challenges and solutions for accelerating AI workloads using GPUs with Kubernetes.

Blackwell GPU contains 208 billion transistors and is paired with 192GB of HBM3e memory