Documentation
NVIDIA Confidential Computing
NVIDIA Confidential Computing extends confidential computing to NVIDIA accelerated-computing platforms, including NVIDIA GPUs and NVIDIA CPUs. Explore deployment modalities, trust boundaries, attestation, and platform support for protecting AI workloads and data in use.
Overview
Deployment Modalities
Tenant-controlled host and complete software stack
For AI labs and model providers operating dedicated hosts. The infrastructure owner remains outside the runtime trust boundary. The tenant’s host software and administrators remain trusted.
Learn moreTenant-controlled guest VM and workload
For workloads requiring a tenant-owned VM image and persistent VM lifecycle. The confidential VM boundary isolates the workload from privileged host software, subject to the required deployment controls.
Learn moreTenant-controlled container workload
For Kubernetes-native workloads running in confidential pods. The confidential pod boundary isolates the workload from privileged host software, subject to control-plane separation and enforced workload policy.
Learn moreRelated Resources
Review supported GPUs, CPUs, drivers, and software versions.
Learn moreLearn how workloads verify NVIDIA hardware and security configuration before releasing secrets.
Learn moreAccess resources for implementing and validating trusted computing on NVIDIA hardware.
Learn moreFor production-use licensing requirements, refer to Licensing.