Edge AI Virtual Agents

Edge AI Virtual Agents

Project Technical Lead:  

Project Committers detail:

Committer

Committer

Company

 Committer Contact Info

Committer Bio

Committer Picture

Self Nominate for PTL (Y/N)

Qi Tang

Individual developer

qitang2023@gmail.com

Ph.D., Hardware Engineer at Google, Ex-Meta, Connectivity Research, ETSI MEC Delegate

Y

Wei Wu

 

willwuwork@gmail.com

LLM researcher at Amazon

 

 

Yi Han

Individual developer

yihan7206@gmail.com

Developer, Finance Manager at Achieve, M.Sc University of Southern California; B.S Peking University

 

 

Sharu Jiang

Individual developer

jsrshark110@gmail.com

Software Engineer at Google, Tech LeadTech lead at Google

 

 

Presentation

a video presentation: https://www.youtube.com/watch?v=r2GfqvbA0hk&t=360s

Use Case Details

Attributes

Description

Informational

Attributes

Description

Informational

Type

New Blueprint for AI Services  at the Edge

 

Blueprint Family - Proposed Name

AI Edge Blueprint Family

 

Use Case

Running Real-Time Generative AI Models at the Edge

 

Blueprint proposed Name

Serverless

 

Initial POD Cost (capex)

Leverage Unicycle POD - less than $150k

 

Scale & Type

Up to 7 servers

  x86/ARM server or deep edge class

  GPU Accelerators

  Memory Cache

 

Applications

Edge Servers Hosting Real-Time Generative AI Services, e.g. Speech-to-Speech Translation, LLM-based Virtual Assistant Services, Text-to-Image/Video Content Generation Services, etc.

 

Power Restrictions

Less than 10Kw

 

Infrastructure orchestration

Kubeless

Docker 1.13.1 or above and K8s 1.10.2 or above- Container Orchestration

OS - Ubuntu 16.x

Under Cloud Orchestration - Airship v1.0

 

SDN

OVS

 

Workload Type

Containers

 

Additional Details

Video Streaming: gRPC, 

Pytorch, Tensorflow

Non-Sql Database: MongodB