Tensor Networks

Address

1289 Reamwood Ave. Suite G
Sunnyvale, CA 94089

Contact

+1 (855) 283-1134

2019 by Tensor Networks, LLC All Rights Reserved
Tensor Networks Sunnyvale, CA USA

The Matrix Machine  

320 Tensor Cores

Network Router, Artificial Intelligence/Machine Learning/

Edge-Computing & Neural Networking in a single Platform

Completely Open:  Modern Networking for Tomorrow's Demanding Use-Cases such as Hybrid Cloud, Multi-Cloud, and secure Micro Cloud machine learning services. Open, industry standard architecture, combined with software-defined networking (SDN), network functions virtualization (NFV), cloud native applications, and Multi-Access Edge Computing (MEC).

 The Tensor Networks Matrix Machine product line is a network router and computing platform that's specialized and optimized for running Machine Learning and Artificial Intelligence applications. The goal of Matrix Machine is to achieve higher performance and availability at lower cost by moving Machine Learning and Artificial Intelligence algorithms into storage and networking, bypassing the traditional processing layers.

For developers and ISV's the Matrix Machine is the best and first fully open and dis-aggregated high-performance computing, and AI/ML platform to develop your solutions to go to market on.

Key Matrix Smart Router Features


Processing:

320 Tensor Core Processors

16 GB GDDR6 300 GB/sec

  • Multi-Precision FP16 Up to 65 TFLOPS | INT8 Up to 130 TOPS | INT4 Up to 260 TFLOPS. Scale-Up or Scale-Out


Physical Routed Interfaces

  • 8 RJ45 1 Gigabit Ethernet Ports

  • 2 RJ45 10 Gigabit Ethernet Ports

  • 2 SFP+ 10 Gigabit Ethernet Ports

  • 2 SFP28 25 Gigabit Ethernet Ports

    • Converge to 1 50 Gigabit Port​

  • 1 RJ45 1 Gigabit Ethernet OOB Management Port


DESIGNED AND ASSEMBLED IN CALIFORNIA

 
 

NFV

Network Functions Virtualization

 

What Tensor Networks Delivers

At Tensor Networks we enable our customers to have a out-of-the-box high performance edge-computing and networking platform experience to leverage artificial intelligence and machine learning.


We wanted to make this easy at a very affordable price. It's a turn-key solution with no additional costs. One part number that works great stand-alone or scales by stacking.


Why Tensor Networks?  

Because:

"The cloud is like a lake. It's a sea of information that you can fish in, you can learn from, you can sift it in different ways and find new ways to look at your data." 


"At the edge it's a fast flowing river.  You'll never build a reservoir big enough to catch all that data. Industrial data is just created too fast, and it's too much, but you can make decisions based on what you see and change the behavior of your assets real-time." -Danielle Merfeld CTO GE Renewables.

High performance edge-computing and networking is very important for many applications that can't wait on the cloud. This is what Tensor Networks delivers.

TensorNetworkDiagram.png
 
 

The Tensor Networks Team

Management

 

Maria Flores

CEO

Mission College
Bay Area Real Estate Investor
Angel Investor
Successful Entrepreneur
Business Networking International Member - Menlo Park, CA

Robert Zhu

Chief Product Officer

Purdue University - Masters of Science Electrical & Computer Engineering

IEEE- Computer Society & Commumications Society

Angel Orrantia

Chief of Staff

Stanford, BSEE

Arizona State, MBA

Notre Dame, JD

Intellectual Property Lawyer

Venture Capitalist

Eric Frazier

Chief Operations Officer

University of the Incarnate Word - BBA -Management
Harvard University - MLA - Sustainability and Environmental Management