Scale Up
Deep Learning Inference
on Your Existing Datacenter Hardware

The Deci platform optimizes your deep learning models to maximize the utilization of any hardware, enabling efficient inference without compromising accuracy.

Book a Demo

The Challenge

The demands of advanced IT infrastructure technologies, such as deep-learning training and inference, will force most enterprises to either update existing data centers or build new ones. This increase in workload is driving the demand for hardware, software, disaster recovery, continuous power supplies, networking and cooling costs. For example, deep-learning inference requires the purchase of new servers with expensive AI-dedicated GPU chips. Demand for deep-learning inference workloads can dramatically increase your data center total-cost-of-ownership (TCO) and cut your product’s profitability.

Deci’s Deep Learning Platform

Connecting your model to the platform and using the AutoNAC technology, will enable a cost-effective deep learning-based application with model optimized throughput for your target hardware. As a result, you can maximize the utilization of your data center hardware, consider switching to cheaper hardware and run multiple models on the same hardware.

Benchmark reduce cloud costs AI

Benefits:

  • Scale up your solution on existing hardware without extra cost
  • Cut your data center total cost of ownership (TCO) by maximizing the throughput of your DL models or by running on existing hardware like CPU

All without compromising on performance or accuracy!

Achieve State-of-the-Art Performance, Powered by AutoNAC™

Boost your trained model’s throughput/latency for any hardware, with Deci’s AutoNAC algorithmic optimization, without compromising on accuracy.

GPU
  • Nvidia T4
  • ResNet-50
  • ImageNet
CPU
  • Intel Xeon Gold 6328H 8-core
  • ResNet-50
  • ImageNet

Applications

  • Medical AI Diagnoses
  • Video Analytics
  • Security Cameras
  • Manufacturing
  • Image Editing
  • Your Application >

Deployment Options

Data Center

CPU and GPU

Edge Server

On-prem /
Edge Server

Data Center

  • CPU and GPU
Edge Server

On-prem /
Edge Server

"Intel and Deci partnered to break a new record at the MLPerf benchmark, accelerating deep learning by 11x on Intel’s Cascade Lake CPU. That’s amazing!
Deci’s platform and technology have what it takes to unleash a whole new world of opportunities for deep learning inference on CPUs."

Guy Boudoukh, Deep Learning Research, Intel AI Research

Relevant Resources

Blog

Efficient Inference in Deep Learning – Where is the Problem?

Read Blog Post

Blog

The Correct Way to Measure Inference Time of Deep Neural Networks

Read Blog Post
How Deci and Intel Hit 11.8x Inference Acceleration at MLPerf

Blog

Deci and Intel Hit 11.8x Inference Acceleration at MLPerf

Read Blog Post

Start Breaking Your AI Barriers