Recogni

About Recogni

Recogni develops a multimodal AI inference system utilizing its proprietary Pareto AI Math to enhance performance while significantly reducing power consumption. This technology addresses the high costs and energy demands of generative AI models, enabling efficient and accurate processing for data centers.

```xml <problem> Generative AI models demand significant computational resources, leading to high operational costs and substantial energy consumption for data centers. Existing inference solutions often struggle to balance performance, accuracy, and efficiency when deploying large language models (LLMs). </problem> <solution> Recogni offers a multimodal AI inference system designed to accelerate generative AI models while drastically reducing power consumption. Their core innovation, Pareto AI Math, enables efficient and accurate processing, making GenAI more economical and sustainable. The system is built using a hardware and software co-design approach, optimizing the entire stack for performance. By utilizing the latest 3nm TSMC technology node and high-bandwidth memory (HBM3e), Recogni's solution achieves high throughput and low latency, even with large models. </solution> <features> - Pareto AI Math: A logarithmic math number system that maintains high accuracy (99.9%) while consuming significantly less power (4x less than standard math). - Hardware-Software Co-design: Optimizes the entire system for performance, balancing compute-to-memory bandwidth and chip-to-chip communication. - 3nm TSMC Technology Node: Ensures best-in-class energy efficiency and cost. - High Bandwidth Memory (HBM3e): Maximizes output speeds for autoregressive models. - Tensor Parallelism (TP > 100): Enables parallelizing AI models across chips for faster processing and larger model support. - Rapid Compilation: Compiles models from PyTorch to executable files in under 10 minutes, even for large models like Llama 405b. - Pareto SDK: Allows developers to deploy models with high accuracy and efficiency. </features> <target_audience> Recogni's primary customers are hyperscalers, cloud service providers, and enterprises that require efficient and accurate generative AI inference for data centers. </target_audience> ```

What does Recogni do?

Recogni develops a multimodal AI inference system utilizing its proprietary Pareto AI Math to enhance performance while significantly reducing power consumption. This technology addresses the high costs and energy demands of generative AI models, enabling efficient and accurate processing for data centers.

Where is Recogni located?

Recogni is based in San Jose, United States.

When was Recogni founded?

Recogni was founded in 2017.

How much funding has Recogni raised?

Recogni has raised 176050000.

Location
San Jose, United States
Founded
2017
Funding
176050000
Employees
112 employees
Major Investors
Juniper Networks, Plug and Play, HSBC Innovation Banking, DNS Capital, Celesta Capital

Find Investable Startups and Competitors

Search thousands of startups using natural language

Recogni

⚠️ AI-generated overview based on web search data – may contain errors, please verify information yourself! You can claim this account with your email domain to make edits.

Executive Summary

Recogni develops a multimodal AI inference system utilizing its proprietary Pareto AI Math to enhance performance while significantly reducing power consumption. This technology addresses the high costs and energy demands of generative AI models, enabling efficient and accurate processing for data centers.

recogni.com7K+
cb
Crunchbase
Founded 2017San Jose, United States

Funding

$

Estimated Funding

$100M+

Major Investors

Juniper Networks, Plug and Play, HSBC Innovation Banking, DNS Capital, Celesta Capital

Team (100+)

No team information available.

Company Description

Problem

Generative AI models demand significant computational resources, leading to high operational costs and substantial energy consumption for data centers. Existing inference solutions often struggle to balance performance, accuracy, and efficiency when deploying large language models (LLMs).

Solution

Recogni offers a multimodal AI inference system designed to accelerate generative AI models while drastically reducing power consumption. Their core innovation, Pareto AI Math, enables efficient and accurate processing, making GenAI more economical and sustainable. The system is built using a hardware and software co-design approach, optimizing the entire stack for performance. By utilizing the latest 3nm TSMC technology node and high-bandwidth memory (HBM3e), Recogni's solution achieves high throughput and low latency, even with large models.

Features

Pareto AI Math: A logarithmic math number system that maintains high accuracy (99.9%) while consuming significantly less power (4x less than standard math).

Hardware-Software Co-design: Optimizes the entire system for performance, balancing compute-to-memory bandwidth and chip-to-chip communication.

3nm TSMC Technology Node: Ensures best-in-class energy efficiency and cost.

High Bandwidth Memory (HBM3e): Maximizes output speeds for autoregressive models.

Tensor Parallelism (TP > 100): Enables parallelizing AI models across chips for faster processing and larger model support.

Rapid Compilation: Compiles models from PyTorch to executable files in under 10 minutes, even for large models like Llama 405b.

Pareto SDK: Allows developers to deploy models with high accuracy and efficiency.

Target Audience

Recogni's primary customers are hyperscalers, cloud service providers, and enterprises that require efficient and accurate generative AI inference for data centers.

Want to add first party data to your startup here or get your entry removed? You can edit it yourself by logging in with your company domain.