SF Big Analytics 2024-06-27: Confidential Containers for GPU Compute: Lift-and-Shift Strategy for AI
We explore transitioning from traditional to secure, isolated environments crucial for sensitive data processing. Our choice of Kata for confidential container enablement ensures security while maintaining container flexibility. Alongside this, a virtualization reference architecture supports advanced scenarios like GPUdirect RDMA. A key aspect of our strategy is the lift-and-shift approach, allowing seamless migration of existing AI/ML workloads to these confidential environments. This integration combines LLMs with GPU-accelerated computing - leveraging Kubernetes for effective orchestration and balancing computational power and data privacy.
Speaker: Zvonko Kaiser ( NVIDIA)
Zvonko is a Principal Systems Engineer at NVIDIA,
working on the Cloud Native Technologies team. Focusing
right now on all things related to confidential computing,
especially in the context of accelerators.