ASUS Announces NVIDIA EGX Solution Support for AI Inferencing on GPU‑Optimized Server Lineup
TAIPEI, Taiwan, May 29, 2019 —ASUS, the leading IT Company in server systems, server motherboards, workstations and workstation motherboards today announced a closer partnership with NVIDIA to support the NVIDIA EGX solution for the next promising segment in AI inferencing. ASUS will deliver a solid hardware solution for edge computing with NVIDIA to enable real-time computing. NVIDIA eliminated the entry barrier to edge computing for enterprise customers with the introduction of the NVIDIA T4 GPU with the NVIDIA EGX solution. NVIDIA EGX also provides a complete solution for operating systems and applications to make creating an edge computing system easier than building one completely from scratch.
With support for the latest Intel 2nd Gen Scalable Processor and NVIDIA T4 GPU, the ASUS ESC4000 G4 server is an ideal choice for the NVIDIA EGX solution. Most importantly, ESC4000 G4 has an excellent mechanical design to offer more flexibility for different customers’ needs. ESC4000 G4 can support four TESLA V100 GPUs, or up to eight NVIDIA T4 GPUs, offering highly intensive inferencing computing power. More GPU computing performance makes real-time edge computing quicker and more accurate. ESC4000 G4 with the NVIDIA EGX solution provides uncompromised performance and delivers an optimized experience for AI applications
High-performance AI computing at the edge
The rapid proliferation of Internet of Things (IoT) devices is creating an explosion in the volume of data. ESC4000 G4 with NVIDIA T4 GPU can run multiple AI models in a pipeline to deliver intelligence at the very edge on hundreds of devices. For video-specific applications, hardware-decode blocks accelerate the processing of high-definition streams for accurate inference.
The best fit for enterprises
NVIDIA Edge Stack is an optimized software stack that includes NVIDIA drivers, a CUDA Kubernetes plug-in, a CUDA Docker container runtime, CUDA-X libraries, and containerized AI frameworks and applications, including TensorRT, TensorRT Inference Server and DeepStream. NVIDIA Edge Stack is optimized for certified servers and downloadable from the NVIDIA NGC registry.
Enables hybrid-cloud and multi-cloud IoT
NVIDIA AI computing is offered by major cloud-computing providers and is architecturally compatible with NVIDIA EGX. AI applications developed in the cloud can run on NVIDIA EGX and vice versa. NVIDIA Edge Stack connects to major cloud IoT services, and customers can remotely manage their service from AWS IoT Greengrass and Microsoft Azure IoT Edge.