> For clean Markdown of any page, append .md to the page URL. > For a complete documentation index, see https://docs.nvidia.com/confidential-computing/virtual-machines/llms.txt. > For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/confidential-computing/_mcp/server. # Dev ## Docs - [Supported Platforms](https://docs.nvidia.com/confidential-computing/virtual-machines/supported-platforms.md): CPUs, GPUs, and operating systems that NVIDIA supports for confidential virtual machines. - [Deploy Confidential Virtual Machines](https://docs.nvidia.com/confidential-computing/virtual-machines/deployment-guide.md): Configure a host, a confidential virtual machine, and NVIDIA GPUs for Confidential Computing. - [Configuring the Hardware](https://docs.nvidia.com/confidential-computing/virtual-machines/deployment-guide/hardware.md): Select CPUs and GPUs for Confidential Computing and configure the BIOS for AMD SEV-SNP or Intel TDX. - [Configuring the Host](https://docs.nvidia.com/confidential-computing/virtual-machines/deployment-guide/host.md): Prepare an AMD SEV-SNP or Intel TDX host and its hypervisor to run confidential virtual machines with NVIDIA GPUs. - [Configuring the GPUs](https://docs.nvidia.com/confidential-computing/virtual-machines/deployment-guide/gpu-mode.md): Bind NVIDIA GPUs to VFIO and set the Confidential Computing or Protected PCIe mode before you pass the GPUs to a confidential virtual machine. - [Creating a Confidential VM](https://docs.nvidia.com/confidential-computing/virtual-machines/deployment-guide/create-vm.md): Create and launch a confidential virtual machine with NVIDIA GPUs attached on an Intel TDX or AMD SEV-SNP host by using KVM and QEMU. - [Configuring the Guest](https://docs.nvidia.com/confidential-computing/virtual-machines/deployment-guide/guest.md): Install and configure the NVIDIA driver in a confidential virtual machine and verify the GPU Confidential Computing state. - [Attesting the GPU](https://docs.nvidia.com/confidential-computing/virtual-machines/deployment-guide/attest.md): Verify the Confidential Computing configuration, attest the GPU, and set the GPU ready state in a confidential virtual machine. - [Trust and Threat Model](https://docs.nvidia.com/confidential-computing/virtual-machines/threat-model.md): Understand the trusted components, responsibilities, mitigated threats, and limits of a confidential VM with NVIDIA Hopper or Blackwell GPUs. - [Licensing](https://docs.nvidia.com/confidential-computing/virtual-machines/licensing.md): NVIDIA Confidential Computing is a licensed feature for production use. > **Note:** This page contains both a page directory (above) and the landing page content (below). The page directory is generated for agent use and does not appear on the landing page. > For clean Markdown of any page, append .md to the page URL. > For a complete documentation index, see https://docs.nvidia.com/confidential-computing/virtual-machines/llms.txt. > For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/confidential-computing/_mcp/server. # Confidential Virtual Machines > Run GPU-accelerated workloads in a confidential virtual machine with NVIDIA Hopper and Blackwell GPUs on AMD SEV-SNP or Intel TDX hosts. A confidential virtual machine (CVM) runs inside a hardware-enforced trusted execution environment on a host with AMD SEV-SNP or Intel TDX. NVIDIA Hopper and Blackwell GPUs that you pass through to the CVM extend that protection to GPU memory and to the data that moves between the CPU and the GPU. The documentation for this product covers the following GPU modes: * Confidential Computing (CC) mode with one GPU per CVM, on Hopper and Blackwell GPUs. * CC mode with multiple GPUs per CVM, on Blackwell GPUs. * Protected PCIe (PPCIe) mode with multiple GPUs per CVM, on Hopper GPUs. Refer to [Supported Platforms](/confidential-computing/virtual-machines/supported-platforms) for the validated combinations of CPUs, GPUs, and operating systems. For trusted components, responsibilities, and protection limits, refer to [Trust and Threat Model](/confidential-computing/virtual-machines/threat-model). ## Workflow The following figure shows the stages of deploying and using a CVM with confidential GPUs. ![Workflow for deploying a confidential virtual machine with confidential GPUs](/confidential-computing/_fern-img/1663af52a21149959a02d5b711b9f952027032c195bc29cece0c62ab9015c00b.webp) Different people can complete different stages. For example, a cloud service provider (CSP) can select and configure the hardware, configure the host, and provision the guest VM. A tenant of the CSP then sets up the guest OS, attests the GPU, and runs applications. ![Example division of the workflow between a cloud service provider and an end user](/confidential-computing/_fern-img/b48e4ceecda4b5e14f73bd975afa208ff9efbe4d7aaefc2b0b4b378caed57dcf.webp) In this example, the CSP does not decide how often the tenant attests the GPU, and the tenant does not configure the GPU for confidential or non-confidential modes. ## Personas The [Deployment Guide](/confidential-computing/virtual-machines/deployment-guide) is organized by the following personas. Start with the section that matches your responsibilities, or read every section in order if you deploy the entire system. | Persona | Responsibilities | Section | | ----------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | Hardware IT Administrator | Selects CPUs and GPUs that support Confidential Computing and configures the BIOS. Includes system architects and IT administrators. | [Configuring the Hardware](/confidential-computing/virtual-machines/deployment-guide/hardware) | | Host OS Administrator | Installs and configures the host OS and hypervisor, configures the GPU mode, and provisions CVMs. Includes system architects, cloud administrators, and advanced on-premises users. | [Configuring the Host](/confidential-computing/virtual-machines/deployment-guide/host), [Configuring the GPUs](/confidential-computing/virtual-machines/deployment-guide/gpu-mode), and [Creating a Confidential VM](/confidential-computing/virtual-machines/deployment-guide/create-vm) | | Virtual Machine Administrator | Receives a CVM with GPUs attached by the hypervisor and installs and configures the NVIDIA driver. Most users start here. | [Configuring the Guest](/confidential-computing/virtual-machines/deployment-guide/guest) | | Virtual Machine User | Attests the GPU and runs confidential applications in a configured CVM. | [Attesting the GPU](/confidential-computing/virtual-machines/deployment-guide/attest) | ## Getting Help To provide feedback or ask questions, use the [NVIDIA Developer Forums for Confidential Computing](https://forums.developer.nvidia.com/c/accelerated-computing/confidential-computing/663).