Platform Overview

Unleash Your Deep
Learning Models

An end-to-end platform enabling AI developers to build, optimize, and deploy blazing-fast deep learning models on any hardware

Accelerate Inference on Edge or Cloud

Get 3x-15x speedup optimization for inference throughput/latency while maintaining accuracy, enabling new use cases on your hardware of choice.

Reach Production Faster

Shorten development cycle from months to weeks with automated tools. No more endless iterations and dozens of different libraries.

Maximize Your Hardware Potential

Scale up with existing hardware. No need for infrastructure changes and extra costs. Gain up to 80% reduction in compute costs.

How It Works

Deep learning lifecycle made simple,
with outstanding performance.

01 BUILD

Efficiently train models from scratch, use a pre-optimized one or bring your own model

Efficiently train models locally or on a cloud machine with the D-Trainer toolkit. D-trainer provides access to multiple SotA computer vision neural architectures and supports popular dataset structures. CURRENTLY IN CLOSED BETA
To start optimization and deployment from an existing state, upload your own model’s checkpoint to your private Model Repository, in the format of any major framework.
Quick start from our Model Hub, and choose from a library of pre-trained and pre-optimized models. Easily fine-tune or re-train the model for your data with the D-Trainer toolkit.

02 OPTIMIZE

Automatically optimize inference performance for your hardware

Enjoy immediate improvement in throughput, latency, and memory with the Deci platform. It optimizes deep learning models using best-of-breed technologies, such as quantization and graph compilers.
Gain 3x-15x acceleration, while preserving accuracy, for any hardware with AutoNAC™. AutoNAC is an algorithmic acceleration technology that is hardware-aware and works on top of other optimization techniques.
Get a complete benchmark of your models’ performance on different hardware and batch sizes in a single interface. Invite co-workers to collaborate on models and communicate your progress.

03 DEPLOY

Production-ready deep learning runtime engines for quick and easy deployment and serving

Push any model—optimized or not—from the Deci Lab directly to one of our inference engines for seamless deployment and ultra-fast serving.
Quickly run inference on your models with Infery, a Python runtime engine that simplifies deep learning model inference across multiple frameworks and hardware—with just 3 lines of code.
Scale your inference workloads with RTiC (Runtime Inference Container), a container-based deep learning runtime engine for high-performance inference. RTiC works best with microservice environments and has built-in performance optimizations.

Built by AI Developers, for AI Developers

Security First

Our platform was designed using best practices for information security, and is compliant with ISO 27001. On-prem options are available.

Developer Friendly

Your experience is our top priority. We made sure you can use the framework and tools of your choice. Deci is accessible through a super-friendly UI or standard API with full documentation and support.

SoTA-oriented

Stay ahead of the curve. Our research team is passionate about always staying up to date when it comes to the latest deep learning SoTA models and techniques.

Integrates Seamlessly

We are dedicated to helping you simplify your deep learning lifecycle. Our platform integrates seamlessly into your existing CI/CD via standard API or Python client.

Security First

Our platform was designed using best practices for information security, and is compliant with ISO 27001. On-prem options are available.

Developer Friendly

SoTA-oriented

Stay ahead of the curve. Our research team is passionate about always staying up to date when it comes to the latest deep learning SoTA models and techniques.

Integrates Seamlessly

We are dedicated to helping you simplify your deep learning lifecycle. Our platform integrates seamlessly into your existing CI/CD via standard API or Python client.

JOIN US ON SLACK

Watch Our Product Demo

"By collaborating with Deci, we aim to help our customers accelerate AI innovation and deploy AI solutions everywhere using our industry-leading platforms, from data centers to edge systems that accelerate high-throughput inference."

Arti Garg

Head of Advanced AI Solutions & Technologies, HPE

“Deci exceeded our expectations in achieving aggressive targets for reducing latency and memory usage on TPU edge hardware in a test environment, all while preserving BriefCam’s high standard for accuracy.”

Yogev Wallach

Sr. Product Manager, BriefCam

"With Deci we were able to get 6.4x higher throughput on our detection model. Its easy-to-use platform allowed us to quickly optimize and benchmark for choosing our best configuration of hardware and parameters."

Santiago Tamagno

CTO, UNX Digital by Grupo Prominente

"The classification model I uploaded and integrated using Infery achieved a 33% performance boost, which is very cool for 10 minutes of work!"

Amir Zait

Algorithm Developer, Sight Diagnostics

“Intel and Deci partnered to break a new record at MLPerf, accelerating deep learning by 11x on Intel’s Cascade Lake CPU. That’s amazing! Deci has what it takes to unleash new opportunities for deep learning inference on CPUs.”

Guy Boudoukh

Deep Learning Research, Intel AI Lab

"We are excited to be working with Deci's platform - it provided amazing results and achieved 4.6x acceleration on a model we ran in production and helped us provide faster service to our customers.”

Daniel Shichman

CEO, WSC Sports Technologies

“With Deci, we increased by 2.6x the inference throughput of one of our multiclass classification models running on V100 machines - without losing accuracy. Deci can cut 50% off the inference costs in our cloud deployments worldwide.”