The Deep Learning Development Platform

Production-Grade Performance, Faster.

Simplify and accelerate the development of computer vision and NLP applications with advanced tools to build, optimize, and deploy highly accurate and efficient models.

The Deep Learning Development Platform

Gain Unparalleled Performance in No Time

Achieve accuracy & runtime performance that outperform SoTA models for any use case and inference hardware.

Shorten Time to
Market

Reach production faster with automated tools. No more endless iterations and dozens of different libraries.

Scale Up
Efficiently

Maximize hardware utilization to enable new use cases on resource constrained devices or cut up to 80% of your cloud compute costs.

See The Results

0 %

Shorter development process. Go from data to production ready model in days.

0 %

Lower development costs per model on average.

0 X

Inference
acceleration

0 X

Inference cost reduction

Here’s where Deci can help you

Gain Unparalleled Performance in No Time.

Increase Throughput

Reduce Latency

Reduce Model Size

Reduce Memory Footprint

Key Features:

Automate Compilation & Post Training Quantization

Easily compile and quantize your models (FP16/INT8) and evaluate different production settings with a click of a button.

Build Efficient
Architectures

Build accurate & efficient architectures tailored for the application, hardware, and performance targets with Deci’s AutoNAC -a NAS based engine.

Quantization
Aware Training

Boost performance without compromising on accuracy by quantizing your model to INT8 during the training process with one line of code.

Accelerate
Pipeline

Boost model serving performance with parallelism and concurrent execution. Compatible with multiple frameworks and hardware types.

Achieve the optimal accuracy-latency tradeoff for your application.

Key Features:

Build Better Models Architectures

Achieve better accuracy with custom architecture built with Deci’s NAS engine - AutoNAC.

Maximize Accuracy with Advanced Training Techniques

Train models with the SuperGradients library and leverage custom training recipes with one line of code.

Save precious time with simplified model profiling and benchmarking.

Key Features:

Find the Bottlenecks in your Model

Benchmark runtime performance of every layer in your neural network to find inference runtime bottlenecks in the architecture as it runs on your target inference Hardware.

Find the Best HW for the Job

Benchmark your models’ expected inference performance across multiple hardware types on Deci’s online hardware fleet. Get actionable insights for the ideal hardware and production settings.

Measure Performance Before You Train

Easily benchmark and compare the performance of different models on your target inference hardware against other hardware including GPUs, CPUs, and commercial edge devices.

Deploy Your Models with 3 lines of Code.

Key Features:

Containerized Production Environment

Save time and hassle by getting a containerized inference engine that can be easily plugged into your production environment.

Seamless Portability with a Unified API

Easily switch between inference frameworks with zero code changes. Compatible with multiple frameworks and hardware types.

“At Adobe, we are committed to redefining the possibilities of digital experiences and delivering excellent AI-based solutions across a wide range of cloud and edge environments. By using Deci, we significantly shortened our time to market and transitioned inference workloads from cloud to edge devices. As a result we improved the user experience and dramatically reduced our spend on cloud inference cost.”

Pallav Vyas

Senior Engineering Manager, Document AI & Innovation at Adobe

“Our advanced text to videos solution is powered by proprietary and complex generative AI algorithms. Deci allows us to reduce our cloud computing cost and improve our user experience with faster time to video by accelerating our models’ inference performance and maximizing GPU utilization on the cloud.”

Lior Hakim

Co-Founder & CTO at HourOne

“Applied Materials is at the forefront of materials engineering solutions and leverages AI to deliver best-in-class products. We have been working with Deci on optimizing the performance of our AI model, and managed to reduce its GPU inference time by 33%. This was done on an architecture that was already optimized. We will continue using the Deci platform to build more powerful AI models to increase our inspection and production capacity with better accuracy and higher throughput.”

Amir Bar

Head of SW and Algorithm, Applied Materials

“Deci’s platform is suitable for both training and inference modes. Deci has advanced innovation in search for optimal neural network architectures. The solution excels in every area of our assessment.”

Michael Azoff

Chief Analyst, Kisaco Research

“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.”

Chaim Linhart

CTO and Co-Founder, IBEX Medical Analysis

“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

“Deci delivers optimized deep learning inference on Intel processors as highlighted in MLPerf, allowing our customers to meet performance SLAs, reduce cost, decrease time to deployment, and gives them the ability to effectively scale.”

Monica Livingston

AI Solutions and Sales Director, Intel

“At RingCentral, we strive to provide our customers with the best AI-based experiences. With Deci’s platform, we were able to exceed our deep learning performance goals while shortening our development cycles. Working with Deci allows us to launch superior products faster.”

Vadim Zhuk

Senior Vice President R&D, RingCentral

“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.”