Red-Hat-NVIDIA_co-brand_logo

 

Accelerate AI with NVIDIA and Red Hat

Accelerate AI with NVIDIA and Red Hat

Speed up delivery of AI-powered intelligent apps across datacenter, edge, and public clouds.

Red Hat® and NVIDIA® are partnering to enable the latest technological innovations for our customers. We share a vision of IT’s future as one fueled by cloud-native, open source technologies. We are working together to enable our customers to run their businesses using familiar infrastructure on many footprints, from virtualized and private cloud deployments in corporate datacenters, to massive-scale services deployed on public clouds, and all the way to the edge.

We are collaborating to create scalable solutions that help accelerate a diverse range of AI use cases leveraging deep learning (DL) and machine learning (ML) acceleration across industries. Examples of these use cases include smart healthcare using NVIDIA Clara™, smart cities and smart manufacturing using NVIDIA Metropolis and more.

 

Accelerated AI infrastructure for datacenters

NVIDIA® and Red Hat provide accelerated AI infrastructure targeted for on-premises deployments.

Based on Red Hat OpenShift®, this joint solution serves as a platform for accelerating ML/DL modeling for data scientists and the delivery of AI powered intelligent applications. 

Organizations can use NVIDIA’s NGC™ software hub to access GPU-optimized DL and ML applications and pre-trained AI models to take advantage of massive parallel processing capabilities. Leading server providers offer NGC-Ready validated servers powered by NVIDIA GPUs, which are optimized to run software from NGC.

SHR-RedHatStack_Transparent_dark-text_sm

 

NVIDIA GPU Operator for Red Hat OpenShift 

NVIDIA GPU Operator for Red Hat OpenShift helps simplify and accelerate the compute-intensive ML/DL modeling tasks for data scientists, and inferencing tasks across datacenters, edge, and public clouds. The GPU Operator enables OpenShift to schedule workloads that require use of NVIDIA GPUs as easily as one would schedule CPU or memory for traditional workloads. Typical use cases that can benefit from GPU acceleration include image and speech recognition, conversational AI, and visual search.

The joint solution is compatible with NGC-Ready validated and Red Hat Enterprise Linux® certified servers.

Operator_RedHatOpenShift

 

Real-time inferencing at the edge

Red Hat and NVIDIA are working to enable high-value AI-powered digital services, such as augmented and virtual reality (AR/VR), IoT, and intelligent traffic systems at the edge. 

By leveraging the NVIDIA EGX edge computing platform--which consists of NGC-Ready validated edge servers and a cloud native, edge-first software stack that includes the NVIDIA GPU Operator for Red Hat OpenShift--organizations can build intelligent AI systems beyond core datacenters and public clouds. 

When deployed over 5G networks, this cloud-native solution can help accelerate data-driven business insights at the edge.

nvidia-deep-learning-inference-2c50-d