Inference Server | Deep Learning Inference

High Performance Hardware

From NVIDIA T4 Inference GPUs, or Xilinx FPGA Accelerators, Exxact Inference Solutions meet your most demanding deep learning inference tasks.

Low-Latency Throughput

Exxact Deep Learning Inference Servers cater to real-time use cases involving multiple inferences per query, such as automatic speech recognition, speech to text, natural language processing, and more.

Pre-Installed Frameworks

Our systems come pre-loaded with TensorFlow, PyTorch, Keras, Caffe, RAPIDS, Docker, Anaconda, MXnet and more upon request.

Suggested Exxact Deep Learning Inference Data Center Systems

Entry-Level

TS2-673917-DPN

Base Specs

CPU 2x Intel Xeon Scalable Processors

GPU 4x NVIDIA Tesla T4

MEM 256GB Memory

STO 1x 2TB SSD (OS/Data)

Mid-Range

TS2-673917-DPN

Base Specs

CPU 2x Intel Xeon Scalable Processors

GPU 8x NVIDIA Tesla T4

MEM 512GB Memory

STO 1x 2TB SSD (OS) Up to 5x 2TB SSD (Data)

High-End

TS4-1910483-DPN

Base Specs

CPU 2x Intel Xeon Scalable Processors

GPU 20x NVIDIA Tesla T4

MEM 512GB Memory

STO 1x 2TB SSD (OS) Up to 5x 2TB SSD (Data)

Not sure what you need?

Let us know what kind of project you have planned. We can help you decide.

High Performance and Scalable

NVIDIA EGX is highly scalable, starting from a single node GPU system and scaling all the way to a full rack of NVIDIA T4 servers, with the ability to deliver more than 10,000 TOPS to serve hundreds of users for real-time speech recognition and other complex AI experiences.

Hybrid Cloud and Multicloud IoT

NVIDIA EGX is architecturally compatible with major cloud providers. 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 services.

Enterprise Grade and Secure

NVIDIA Edge Stack has been optimized on Red Hat OpenShift, the leading enterprise-grade Kubernetes container orchestration platform. Mellanox Smart NICs can offload and accelerate software defined networking to enable a higher level of isolation and security without impacting CPU performance.

Enterprise-Grade Software Stack for the Edge

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 NVIDIA TensorRT™, TensorRT Inference Server, and DeepStream.