SAKURA-II Edge AI Acceleration Solution Announced by EdgeCortix CEO Sakya Dasgupta


The exciting new SAKURA-II device pushes the envelope for Edge AI with support for Generative AI and other complex models

In this video, CEO and Founder Sakya Dasgupta discusses how EdgeCortix used a software-first approach to develop a complete Edge AI Platform with silicon, AI engines, software, and development platforms.

The SAKURA-II Platform includes:

  • SAKURA-II device: High performance, 60 TOPS, edge AI accelerator architected to run the latest vision and Generative AI models with market-leading energy efficiency and low latency.
  • Dynamic Reconfigurable Architecture (DNA): A flexible neural architecture with run-time reconfigurable interconnects between compute units and support for up to 32GB of DRAM, achieving exceptional parallelism and efficiency through dynamic grouping.
  • MERA Compiler and Software Framework: A robust platform for deploying the latest AI inference models quickly and easily, in an application agnostic manner.
  • M.2 Modules and PCIe Cards: Development platforms in M.2 and PCIe form factors, enabling flexible system integration, quick and easy evaluation, and fast time-to-market.

Learn how the SAKURA-II Edge AI Platform solution can power your next design.

Next Wave of Generative AI at the Edge

Introducing SAKURA-II, the world’s most flexible and energy efficient AI accelerator

AI Accelerator
High Performance, Low Power, Generative AI ready, effectively handles multi-billion parameter models

Efficient Hardware
Learn More
AI Accelerator
Modules and Cards
Up to 240 TOPS in systems
powered by the latest SAKURA-II
AI Accelerators

Deployable Systems
Learn More
MERA Compiler and Framework
Industry first software platform enabling AI inference across heterogeneous systems

Unique Software
Learn More
Dynamic Neural Accelerator™ Technology
Flexible, run-time reconfigurable, highly-parallelized and efficient architecture

Proprietary Architecture
Learn More