NVIDIA Virtual Compute Server

Powering the Most Compute-Intensive Server Workloads

Accelerated Compute, Virtualized

AI, deep learning, and data science workflows require an unprecedented amount of compute power. NVIDIA Virtual Compute Server (vCS) enables data centers to accelerate server virtualization with the latest NVIDIA data center GPUs, including NVIDIA A100 and A30 Tensor Core GPUs, so that the most compute-intensive workloads, such as artificial intelligence, deep learning, and data science, can be run in a virtual machine (VM) powered by NVIDIA vGPU technology. This isn’t a marginal step for virtualization — it’s a big leap.

Upscaled for Maximum Efficiency

NVIDIA Virtual GPUs give you near bare metal performance in a virtualized environment, maximum utilization, management and monitoring, in a hypervisor-based virtualization environment for GPU-accelerated AI.

Deep Learning Training Performance Scaling with vCS on NVIDIA A100 Tensor Core GPUs

Developers, data scientists, researchers, and students need a massive amount of compute power for deep learning training. Our A100 Tensor Core GPU accelerates the workload, letting them do more faster. NVIDIA software, the Virtual Compute Server, delivers nearly the same performance as bare metal, even when scaling to large deep learning training models that use multiple GPUs.

Deep Learning Inference Throughput Performance with MIG on NVIDIA A100 Tensor Core GPUs using vCS

Multi-instance GPU (MIG) is a technology, only found on the NVIDIA A100 Tensor Core GPU, that partitions the A100 GPU into as many as seven instances, each fully isolated with their own high-bandwidth memory, cache, and compute cores. MIG can be used with Virtual Compute Server, one VM per MIG instance.  The  performance is consistent when running an inference workload across multiple MIG instances on both bare metal and virtualized with vCS.

Resources For IT Managers

Learn more about how NVIDIA Virtual Compute Server helps maximize performance and simplify IT management.

Utilization Optimization

Utilization Optimization

Take advantage of valuable GPU resources to seamlessly provision GPU sharing for lighter workloads like inference, or multiple virtual GPUs for more compute-intensive workloads like deep learning training.

Manageability and Monitoring

Manageability and Monitoring

Ensure high availability and uptime of the systems relied on by data scientists and researchers. Easily monitor GPU  performance at the guest, host, and application level. You can even leverage management tools like suspend/resume and live migration. Learn more about the operational benefits of GPU virtualization.

Browse Supported vGPUs

Virtual Compute Server is supported with the most powerful NVIDIA GPUs available, including the NVIDIA A100 Tensor Core GPU, NVIDIA A40 Tensor Core GPU, NVIDIA T4 Tensor Core GPU, and the NVIDIA V100 Tensor Core GPU.

See the full list of recommended NVIDIA GPUs for virtualization.

NVIDIA partners with a broad ecosystem of OEM partners who can be found on the Find a Certified Server page.

Try Before You Buy

Register for a 90-day free trial

Buy vCS

Purchase the NVIDIA vGPU solution from an NVIDIA Partner Network (NPN) partner. Our extensive network of trained partners can help with architecting and deploying an optimal accelerated virtualized environment.

FAQ

Explore More Virtual GPU Software Solutions

NVIDIA RTX Virtual Workstation (vWS)

NVIDIA RTX Virtual Workstation (vWS)

Virtual Workstations for creative and technical professionals using graphics applications.

NVIDIA Virtual PC (vPC)

NVIDIA Virtual PC (vPC)

Virtual Desktop (VDI) for knowledge workers who use office productivity applications & multimedia.

NVIDIA Virtual Applications (vApps)

NVIDIA Virtual Applications (vApps)

Application streaming with Remote Desktop Session Host (RDSH) solutions.

How to Buy

Find an NVIDIA partner who sells
NVIDIA vGPU solutions.

Download Software

Access the latest
NVIDIA vGPU software.

Get Support

Contact NVIDIA Enterprise
Support.